Gradient-based learning applied to document recognition

1998/01/01 by Yann LeCun, Y. Lecun, L. Bottou +5 · 2597 citations
Computer Science · #Handwritten Text Recognition Techniques #Image Processing and 3D Reconstruction #Neural Networks and Applications

paper · doi:10.1109/5.726791

Abstract

Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

Cited by

• Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model
• Quantum Dot Optoelectronic Synaptic Devices With Long Memory Time Enabled by Trap Density Regulation
• A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification
• Deep learning for denoising
• Automatic Modulation Classification: A Deep Learning Enabled Approach
• Deep learning and its application in geochemical mapping
• Recent advances and future research directions in deep learning as applied to geochemical mapping
• Automated Detection of Oral Pre-Cancerous Tongue Lesions Using Deep Learning for Early Diagnosis of Oral Cavity Cancer
• Adaptive Federated Learning With Non-IID Data
• Adversarial Attacks on Network Intrusion Detection Systems Using Flow Containers
• Efficient Mitchell’s Approximate Log Multipliers for Convolutional Neural Networks
• Hierarchical Fault Diagnosis Method for Piezoresistive Pressure Sensor Based on GAF and CNN-SVM
• Real-time monitoring of work-at-height safety hazards in construction sites using drones and deep learning
• Efficient Processing of Deep Neural Networks: A Tutorial and Survey
• PAICORE: A 1.9-Million-Neuron 5.181-TSOPS/W Digital Neuromorphic Processor With Unified SNN-ANN and On-Chip Learning Paradigm
• Classification of the Clinical Images for Benign and Malignant Cutaneous Tumors Using a Deep Learning Algorithm
• Deep Learning With Edge Computing: A Review
• Neuro-Inspired Computing With Emerging Nonvolatile Memorys
• FeatureNet: Machining feature recognition based on 3D Convolution Neural Network
• Robustness evaluation for deep neural networks via mutation decision boundaries analysis
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Strong mixed-integer programming formulations for trained neural networks
• Convergence of Langevin-simulated annealing algorithms with multiplicative noise
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better
• DOOM Level Generation Using Generative Adversarial Networks
• Recent advances in convolutional neural networks
• Rasabodha: Understanding Indian classical dance by recognizing emotions using deep learning
• Optimization Methods for Large-Scale Machine Learning
• Diffuse Interface Models on Graphs for Classification of High Dimensional Data
• Ephaptic Coupling in Ultralow‐Power Ion‐Gel Nanofiber Artificial Synapses for Enhanced Working Memory
• Wear particle classification considering particle overlapping
• Exact Neural-Network Representations of the Motzkin States
• Touchless fingerprint recognition: A survey of recent developments and challenges
• Machine Learning for Molecular Simulation
• Rate-Splitting Multiple Access for Near-Field Communications With Imperfect CSIT and SIC
• A Comprehensive Survey on Graph Neural Networks
• The potential of quantum computers for Particle Image Velocimetry
• Auto-adaptive Resonance Equalization using Dilated Residual Networks
• Graph Distribution-valued Signals in Wasserstein Spaces: Theory and Applications
• Test Case Prioritization for DNNs via Neural Collapse Instability
• Inferring activity from fluid flow in continuum models of active matter
• AuditVotes: Elevating Provable Defense for GNNs with Efficient Augmentation and Conditional Smoothing
• A Multiclass Quantum Aligned Centroid Kernel
• Q-PhotoNAS: Hybrid Quantum Neural Architecture Search Framework on Photonic Devices
• On the Separability of Information in Diffusion Models
• Evaluating Uncertainty and Quality of Visual Language Action-enabled Robots
• Streaming Sliced Optimal Transport
• An operator-splitting algorithm for the hypergraph p-Laplacian with applications to missing data recovery
• End-to-End Differential Privacy in Training Deep Neural Network Classifiers
• Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation
• Stop using Media Bias/Fact Check in research
• Neural Belief-Matching Decoding for Topological Quantum Error Correction Codes
• Onboarding Without Forgetting: Hypernetwork Personalization with Data-Free Replay for Personalized Federated Learning
• FedDP-PALD: A Privacy-Preserving Federated Latent Diffusion Framework with Prototype Aggregation for Medical Data Synthesis
• Provably Lossless Acceleration of DNN Mutation Testing via Memoization
• Intelligence from Learnable Novelty
• Lipschitz-Based Robustness Certification Under Floating-Point Execution
• An Iterative Geometric Approach to Optimizing Separating Hyperplanes
• VecFontLLM: Anchor-Guided Direct Synthesis of Chinese Vector Fonts
• Do We Really Need Quantum Machine Learning?: A Multidimensional Empirical Study
• BADTV: Unveiling Backdoor Threats in Third-Party Task Vectors
• Effects of width-dependent model hyperparameters and ℓ₂-regularization on the loss landscape of two-layer ReLU networks
• Density-Informed Pseudo-Counts for Calibrated Evidential Deep Learning
• Online-Score-Aided Federated Learning for Resource-Constrained Wireless Clients with Continual Data Arrival
• CT-Merging: Consensus Directions and Task-Level Scaling for LoRA Adapter Merging
• Semi-Supervised Conditional Generative Learning through Stochastic Interpolation and Sufficient Representations
• Dataset Distillation by Influence Matching
• Exploiting Symmetry in Quantum Reservoir Computing
• Joint Utilization of Geospatial and census proxies for Autoencoder-Assisted Downscaling (JUGAAD) of socioeconomic indicators in India
• Machine-learning test of the single-ion model for dd excitations in cuprates
• Handwritten and Printed Text Segmentation via Region-Aware Human-Writing Descriptor Engineering
• NORACL: Neurogenesis for Oracle-free Resource-Adaptive Continual Learning
• The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis
• Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers
• NFSA: Non-Forward Secure Aggregation with One Server via Two Layer Secret Sharing
• Factorized Neural Operators Decompose Dynamic and Persistent Responses
• Quality-Aware Robust Multi-View Clustering for Heterogeneous Observation Noise
• Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
• NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation
• Generative Bayesian Filtering for State Estimation
• Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks
• Scaling quantum machine learning without tricks: full-resolution and diverse image generation
• Do Transformers Need Three Projections? Systematic Study of QKV Variants
• CURE: Privacy-Preserving Split Learning Done Right
• There Will Be a Scientific Theory of Deep Learning
• Human-level 3D shape perception emerges from multi-view learning
• Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data
• Deep Learning-based Filtering for Video Coding: A Survey on Architectures, Algorithms, and Complexity Analysis
• Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning
• Pre-training under infinite compute
• uGMM-NN: Univariate Gaussian Mixture Model Neural Network
• Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
• Who Does What in Deep Learning? Multidimensional Game-Theoretic Attribution of Function of Neural Units
• Neurosymbolic Diffusion Models
• Vulnerability Detection via Multiple-Graph-Based Code Representation
• Neurosymbolic Decision Trees
• Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks
• Scaling Laws in Patchification: An Image Is Worth 50,176 Tokens And More
• Layer-wise learning of deep generative models
• Gradient descent in materia through homodyne gradient extraction
• Vision-Enhanced Large Language Models for High-Resolution Image Synthesis and Multimodal Data Interpretation
• Uneven illumination surface defects inspection based on convolutional neural network
• Dynamic texture and scene classification by transferring deep image features
• Controllable Data Augmentation Through Deep Relighting
• A Convolutional Attention Network for Extreme Summarization of Source Code
• Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
• A neural anisotropic view of underspecification in deep learning
• Accurate and Fast Federated Learning via IID and Communication-Aware Grouping
• Distributionally Robust Policy Learning via Adversarial Environment Generation
• Explainable Deep Modeling of Tabular Data using TableGraphNet
• Lossy Image Compression with Compressive Autoencoders
• Predicting Parameters in Deep Learning
• Non-Intrusive Load Monitoring with Fully Convolutional Networks
• Recombination of Artificial Neural Networks
• Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks
• An AI-Powered Autonomous Underwater System for Sea Exploration and Scientific Research
• Generative Concatenative Nets Jointly Learn to Write and Classify Reviews
• Outstanding Bit Error Tolerance of Resistive RAM-Based Binarized Neural Networks
• Toward computational neuroconstructivism: a framework for developmental systems neuroscience
• Gender in Danger? Evaluating Speech Translation Technology on the\n MuST-SHE Corpus
• Image Classification with Hierarchical Multigraph Networks
• Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation
• Local Information with Feedback Perturbation Suffices for Dictionary Learning in Neural Circuits
• Accumulated Decoupled Learning: Mitigating Gradient Staleness in Inter-Layer Model Parallelization
• Generalization Bounds For Unsupervised and Semi-Supervised Learning With Autoencoders
• LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders
• EnvGAN: Adversarial Synthesis of Environmental Sounds for Data Augmentation
• Approximating Instance-Dependent Noise via Instance-Confidence Embedding
• A Convolutional Neural Network for gaze preference detection: A\n potential tool for diagnostics of autism spectrum disorder in children
• Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation
• Image Inpainting via Stochastic Dynamics
• Variational Inference with Continuously-Indexed Normalizing Flows
• Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks
• Building Compact and Robust Deep Neural Networks with Toeplitz Matrices
• Distributed Networked Real-time Learning
• Multi-scale recognition with DAG-CNNs
• CNNs are Globally Optimal Given Multi-Layer Support
• Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives
• Exploiting Chain Rule and Bayes' Theorem to Compare Probability Distributions
• SWIFT: Super-fast and Robust Privacy-Preserving Machine Learning
• Hue-Net: Intensity-based Image-to-Image Translation with Differentiable\n Histogram Loss Functions
• Inverse Classification for Comparison-based Interpretability in Machine Learning
• Sequential Labeling with online Deep Learning
• HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Image
• NeuNetS: An Automated Synthesis Engine for Neural Network Design
• A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness
• Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
• Syntax Matters! Syntax-Controlled in Text Style Transfer
• End-to-End Refinement Guided by Pre-trained Prototypical Classifier
• PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
• Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition
• Taming the Cross Entropy Loss
• Wide Compression: Tensor Ring Nets
• Clustering Learning for Robotic Vision
• MC-LSTM: Mass-Conserving LSTM
• Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
• MUTE: Data-Similarity Driven Multi-hot Target Encoding for Neural Network Design
• Multi-Subspace Neural Network for Image Recognition
• Pruning-Aware Merging for Efficient Multitask Inference
• CNNs, LSTMs, and Attention Networks for Pathology Detection in Medical Data
• Neural Networks and Polynomial Regression. Demystifying the Overparametrization Phenomena
• Object-Adaptive LSTM Network for Real-time Visual Tracking with Adversarial Data Augmentation
• Learning Graph-Level Representation for Drug Discovery
• A Gradient Free Neural Network Framework Based on Universal\n Approximation Theorem
• Set Representation Learning with Generalized Sliced-Wasserstein Embeddings
• A Convolutional Architecture for 3D Model Embedding
• GuideBP: Guiding Backpropagation Through Weaker Pathways of Parallel Logits
• Evolving Deep Convolutional Neural Networks for Image Classification
• A Unified Gradient Regularization Family for Adversarial Examples
• AUC-maximized Deep Convolutional Neural Fields for Sequence Labeling
• Laplace Redux -- Effortless Bayesian Deep Learning
• Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework
• iDLG: Improved Deep Leakage from Gradients
• Generative Adversarial Mapping Networks
• A Variational Perspective on Diffusion-Based Generative Models and Score Matching
• The Power Spherical distribution
• Deep Learning for Needle Detection in a Cannulation Simulator
• Large-Scale Optimal Transport and Mapping Estimation
• Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
• The Perception-Distortion Tradeoff
• Dive into Deep Learning
• Generalized Ternary Connect: End-to-End Learning and Compression of Multiplication-Free Deep Neural Networks
• Convolutional Neural Networks In Convolution
• Scaling Wide Residual Networks for Panoptic Segmentation
• Learning Hybrid Representation by Robust Dictionary Learning in Factorized Compressed Space
• Enhancing Convolutional Neural Networks for Face Recognition with\n Occlusion Maps and Batch Triplet Loss
• Multi-class Gaussian Process Classification with Noisy Inputs
• Algorithmic insights on continual learning from fruit flies
• Perceiver: General Perception with Iterative Attention
• Alleviating Bottlenecks for DNN Execution on GPUs via Opportunistic Computing
• Graph Neural Network for Hamiltonian-Based Material Property Prediction
• ExAD: An Ensemble Approach for Explanation-based Adversarial Detection
• DNN or k-NN: That is the Generalize vs. Memorize Question
• Auxiliary Deep Generative Models
• Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption
• Image denoising with multi-layer perceptrons, part 2: training trade-offs and analysis of their mechanisms
• TzK: Flow-Based Conditional Generative Model
• A parallel Fortran framework for neural networks and deep learning
• Kernelized Classification in Deep Networks
• PolyNeuron: Automatic Neuron Discovery via Learned Polyharmonic Spline Activations
• Weighted Sparse Subspace Representation: A Unified Framework for Subspace Clustering, Constrained Clustering, and Active Learning
• To What Extent Are Star Cluster Ages Encoded in Their Environments? Exploring the Spatial Distribution of Age-Related Information with PHANGS-HST Imaging and Convolutional Neural Networks
• Covariant Compositional Networks For Learning Graphs
• Constrained Linear Data-feature Mapping for Image Classification
• DTN: A Learning Rate Scheme with Convergence Rate of \O(1/t)\n for SGD
• Variations on the Chebyshev-Lagrange Activation Function
• Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks
• Reduced Complexity Simulation of Wireless Sensor Networks for Application Development
• Robust Federated Learning with Attack-Adaptive Aggregation
• On Transportation of Mini-batches: A Hierarchical Approach
• Dense Multimodal Fusion for Hierarchically Joint Representation
• Detecting Adversarial Examples through Nonlinear Dimensionality Reduction
• Evolution in Groups: A deeper look at synaptic cluster driven evolution of deep neural networks
• KIT MOMA: A Mobile Machines Dataset
• Multi-Level Recurrent Residual Networks for Action Recognition
• Motion-Based Handwriting Recognition
• Semantics, Representations and Grammars for Deep Learning
• A DNN Framework For Text Image Rectification From Planar Transformations
• Communication Compression for Distributed Learning with Aggregate and Server-Guided Feedback
• Shunting Inhibition and Dendritic Branching Shape Local Credit Assignment
• LuxIA: A Lightweight Unitary matriX-based Framework Built on an Iterative Algorithm for Photonic Neural Network Training
• Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection
• Attack-Resistant Federated Learning with Residual-based Reweighting
• Dense and Diverse Capsule Networks: Making the Capsules Learn Better
• Segmentation of digital rock images using deep convolutional autoencoder networks
• MemNet: A Persistent Memory Network for Image Restoration
• Mutual Modality Trust with Lightweight Reconstruction Regularization for Fine-grained Tire Pattern Recognition
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• End-to-End Integration of a Convolutional Network, Deformable Parts Model and Non-Maximum Suppression
• Locally Smoothed Neural Networks
• On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers
• Estimating Information Flow in Deep Neural Networks
• Evaluation of Neural Networks for Image Recognition Applications: Designing a 0-1 MILP Model of a CNN to create adversarials
• Linearized Multi-Sampling for Differentiable Image Transformation
• Evaluation of Complex-Valued Neural Networks on Real-Valued Classification Tasks
• Global Adversarial Attacks for Assessing Deep Learning Robustness
• Transfer Learning Using Classification Layer Features of CNN
• The Loss Surfaces of Multilayer Networks
• A Layer-wise Adversarial-aware Quantization Optimization for Improving Robustness
• An Information-Theoretic Explanation for the Adversarial Fragility of AI Classifiers
• Visual Context-aware Convolution Filters for Transformation-invariant Neural Network
• Block-Cyclic Stochastic Coordinate Descent for Deep Neural Networks
• Masked LARk: Masked Learning, Aggregation and Reporting worKflow
• Context-aware CNNs for person head detection
• FedML: A Research Library and Benchmark for Federated Machine Learning
• ABCNN: Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
• Scalable Verification of Quantized Neural Networks (Technical Report)
• Scaling Binarized Neural Networks on Reconfigurable Logic
• An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms
• Towards High-Level Semantic Intelligence
• Localized Uncertainty Attacks
• The Weaponization of Computer Vision: Tracing Military-Surveillance Ties through Conference Sponsorship
• Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons
• Model Complexity-Accuracy Trade-off for a Convolutional Neural Network
• GINN: Geometric Illustration of Neural Networks
• Learning Neighborhoods for Metric Learning
• Enabling Sparse Winograd Convolution by Native Pruning
• An Attention-Based Deep Net for Learning to Rank
• Charged Point Normalization: An Efficient Solution to the Saddle Point\n Problem
• Hidden Markov Neural Networks
• Computational Separation Between Convolutional and Fully-Connected Networks
• UCP: Uniform Channel Pruning for Deep Convolutional Neural Networks Compression and Acceleration
• Updater-Extractor Architecture for Inductive World State Representations
• Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach
• Audiovisual speaker conversion: jointly and simultaneously transforming facial expression and acoustic characteristics
• Regularization and Optimization strategies in Deep Convolutional Neural Network
• A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples
• Parallelized Tensor Train Learning of Polynomial Classifiers
• Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation
• Wavelet Integrated CNNs for Noise-Robust Image Classification
• Not just about size - A Study on the Role of Distributed Word Representations in the Analysis of Scientific Publications
• Learning Deep Analysis Dictionaries -- Part II: Convolutional Dictionaries
• Achievable Rates for Pattern Recognition
• Proxy Network for Few Shot Learning
• Estimation of Individual Device Contributions for Incentivizing Federated Learning
• Fourier Shell Analysis: k‐Space‐Based Metrics for Assessing Super‐Resolution in <scp>4D</scp> Flow <scp>MRI</scp>
• Nonlinear Tensor Ring Network
• Compressed Sensing with Deep Image Prior and Learned Regularization
• A Novel Geometric Approach for Outlier Recognition in High Dimension
• A Generalizable Approach to Learning Optimizers
• Adversarial Attack Type I: Cheat Classifiers by Significant Changes
• A variation of Broyden Class methods using Householder adaptive transforms
• Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization
• Collaborative Representation Classification Ensemble for Face Recognition
• SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
• Classify Images with Conceptor Network
• A Rate-Distortion Framework for Explaining Neural Network Decisions
• Multi-objects Generation with Amortized Structural Regularization
• Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
• Robust Training in High Dimensions via Block Coordinate Geometric Median Descent
• Multi-Class Classification from Single-Class Data with Confidences
• Statistical theory for image classification using deep convolutional neural networks with cross-entropy loss under the hierarchical max-pooling model
• Learning a Deep Part-based Representation by Preserving Data Distribution
• Geosocial Location Classification: Associating Type to Places Based on Geotagged Social-Media Posts
• A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
• Black-box Adversarial Sample Generation Based on Differential Evolution
• An empirical investigation into the properties of standard word embeddings
• How Does a Deep Neural Network Look at Lexical Stress?
• Decoding Phone Pairs from MEG Signals Across Speech Modalities
• Deep Anchored Convolutional Neural Networks
• The Semantic Least-Energy Principle: A Hypothesis for Intelligence
• SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation
• The balance between compactness and forecast accuracy of data-driven latent-space reduced-order models in controlled wake flows
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Mini-batch Noise Lowers Sharpness via Dominant-Subspace Fluctuations
• Bayesian Deep Learning via Subnetwork Inference
• Adversarial Discriminative Domain Adaptation
• Single-shot Channel Pruning Based on Alternating Direction Method of Multipliers
• A Tale of Three Probabilistic Families: Discriminative, Descriptive and Generative Models
• Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
• DADA: Differentiable Automatic Data Augmentation
• AI Empowered Communication and Radar Modulation Recognition: A Survey
• Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reduction
• Flowing ConvNets for Human Pose Estimation in Videos
• Contrastive Principal Component Analysis
• Distributed Nonlinear Equality-Constrained Optimization via Feedback Linearization and Singular Perturbation
• Automated Numerical Stability Analysis of Deep Learning Operators
• Directional Influence Function: Estimating Training Data Influence in Constrained Learning
• Equivariant Q Learning in Spatial Action Spaces
• Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?
• Multi-Scale Structural Features for Continual, Comprehensible Visual Recognition in a Developmental Learning Framework
• Reducing Instruction-Fetch Energy in RISC-V for Embedded AI Processing via Dynamic and Static Loop Caching
• Towards Flexible Device Participation in Federated Learning
• Unlocking Spatial Grounding in Large Audio-Visual Retrieval models
• Practical Black-Box Attacks against Machine Learning
• Forward Thinking: Building Deep Random Forests
• AQ-Stacker: An Adaptive Quantum Matrix Multiplication Algorithm with Scaling via Parallel Hadamard Stacking
• Multimodal User Authentication Method via Fusion of Keystroke Dynamics and Glove-Based Hand Kinematics
• Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits
• Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
• Estimating g-Leakage via Machine Learning
• Forward and Inverse Mantle Convection with Neural Operators
• Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
• Robust Federated Fine-Tuning in Heterogeneous Networks with Unreliable Connections: An Aggregation View
• Benchmarking deep learning models for Raman spectroscopy across open-source datasets
• Qualitatively characterizing neural network optimization problems
• Distance-Based Learning from Errors for Confidence Calibration
• LVLM-Aided Alignment of Task-Specific Vision Models
• Online Learning Extreme Learning Machine with Low-Complexity Predictive Plasticity Rule and FPGA Implementation
• Personalized Federated Learning with Moreau Envelopes
• CNN as Guided Multi-layer RECOS Transform
• Incremental Learning Using a Grow-and-Prune Paradigm with Efficient Neural Networks
• Defending against adversarial attacks using mixture of experts
• Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
• UbiQVision: Quantifying Uncertainty in XAI for Image Recognition
• Memory Bounded Deep Convolutional Networks
• PairFlow: Closed-Form Source-Target Coupling for Few-Step Generation in Discrete Flow Models
• Discovering Symmetry Groups with Flow Matching
• MAPI-GNN: Multi-Activation Plane Interaction Graph Neural Network for Multimodal Medical Diagnosis
• Gaussian Process Assisted Meta-learning for Image Classification and Object Detection Models
• A Probabilistic Theory of Deep Learning
• Deep learning-driven atmospheric parameter prediction for hot subdwarf stars with synthetic and observed spectra
• Graph neural network-based fault diagnosis: a review
• Image-specific Convolutional Kernel Modulation for Single Image Super-resolution
• Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
• Mining Fix Patterns for FindBugs Violations
• On the Accuracy of Influence Functions for Measuring Group Effects
• DK-STN: A Domain Knowledge Embedded Spatio-Temporal Network Model for MJO Forecast
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Dynamic Stream Network for Combinatorial Explosion Problem in Deformable Medical Image Registration
• Alternating Direction Method of Multipliers for Nonlinear Matrix Decompositions
• Deep Kernel Learning
• Timely Parameter Updating in Over-the-Air Federated Learning
• Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
• Improving Deep Neural Networks with Probabilistic Maxout Units
• Is Your Conditional Diffusion Model Actually Denoising?
• DeepGuard: Defending Deep Joint Source-Channel Coding Against Eavesdropping at Physical-Layer
• Inverse-Designed Phase Prediction in Digital Lasers Using Deep Learning and Transfer Learning
• Towards Ancient Plant Seed Classification: A Benchmark Dataset and Baseline Model
• Transfer Learning for Analysis of Collective and Non-Collective Thomson Scattering Spectra
• FedOAED: Federated On-Device Autoencoder Denoiser for Heterogeneous Data under Limited Client Availability
• InfinityEBSD : Metrics-Guided Infinite-Size EBSD Map Generation With Diffusion Models
• From Priors to Predictions: Explaining and Visualizing Human Reasoning in a Graph Neural Network Framework
• OPENTOUCH: Bringing Full-Hand Touch to Real-World Interaction
• Persistent Multiscale Density-based Clustering
• DRIVE: One-bit Distributed Mean Estimation
• Privacy Blur: Quantifying Privacy and Utility for Image Data Release
• Convolutional Lie Operator for Sentence Classification
• From Risk to Resilience: Towards Assessing and Mitigating the Risk of Data Reconstruction Attacks in Federated Learning
• An updated efficient galaxy morphology classification model based on ConvNeXt encoding with UMAP dimensionality reduction
• Residual GRU+MHSA: A Lightweight Hybrid Recurrent Attention Model for Cardiovascular Disease Detection
• An Additively Preconditioned Trust Region Strategy for Machine Learning
• Residual Networks Behave Like Ensembles of Relatively Shallow Networks
• Multi-Mode Inference Engine for Convolutional Neural Networks
• Nondeterminism and Instability in Neural Network Optimization
• Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence
• SuperCLIP: CLIP with Simple Classification Supervision
• MURIM: Multidimensional Reputation-based Incentive Mechanism for Federated Learning
• Automatically Composing Representation Transformations as a Means for Generalization
• Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks
• How good is my GAN?
• Rational Recurrences
• Online hyperparameter optimization by real-time recurrent learning
• Analyzing Federated Learning through an Adversarial Lens
• A Class of Accelerated Fixed-Point-Based Methods with Delayed Inexact Oracles and Its Applications
• Dual-Qubit Hierarchical Fuzzy Neural Network for Image Classification: Enabling Relational Learning via Quantum Entanglement
• Bridged Adversarial Training
• Quanvolutional Neural Networks for Spectrum Peak-Finding
• Evaluating Singular Value Thresholds for DNN Weight Matrices based on Random Matrix Theory
• DeepSmartFuzzer: Reward Guided Test Generation For Deep Learning
• Towards High-Fidelity Gaussian Splatting with Queried-Convolution Neural Networks
• GradID: Adversarial Detection via Intrinsic Dimensionality of Gradients
• Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning
• Differentiable Energy-Based Regularization in GANs: A Simulator-Based Exploration of VQE-Inspired Auxiliary Losses
• Improving compute efficacy frontiers with SliceOut
• Semi-Supervised Domain Generalization with Evolving Intermediate Domain
• Iterative Sampling Methods for Sinkhorn Distributionally Robust Optimization
• Uncertainty Quantification for Machine Learning: One Size Does Not Fit All
• Evolutionary Synthesis of Deep Neural Networks via Synaptic Cluster-driven Genetic Encoding
• Phase transitions reveal hierarchical structure in deep neural networks
• Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling
• Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
• Quantized Convolutional Neural Networks for Mobile Devices
• Learning the Pareto Front with Hypernetworks
• Where Classification Fails, Interpretation Rises
• Understanding Deep Learning Techniques for Image Segmentation
• Bhargava Cube--Inspired Quadratic Regularization for Structured Neural Embeddings
• Uncertainty-Aware Deep Classifiers using Generative Models
• Hierarchical Dataset Selection for High-Quality Data Sharing
• RATT: Leveraging Unlabeled Data to Guarantee Generalization
• Quantum Algorithms for Unsupervised Machine Learning and Neural Networks
• Predicting brain age with deep learning from raw imaging data results in\n a reliable and heritable biomarker
• FMA: A Dataset For Music Analysis
• Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games
• Learning Sparse Neural Networks through L₀ Regularization
• Supervised Learning of Random Neural Architectures Structured by Latent Random Fields on Compact Boundaryless Multiply-Connected Manifolds
• On Classification of Distorted Images with Deep Convolutional Neural Networks
• REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature
• Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification
• Dynamic Efficient Adversarial Training Guided by Gradient Magnitude
• Image Segmentation, Compression and Reconstruction from Edge\n Distribution Estimation with Random Field and Random Cluster Theories
• Unambiguous Representations in Neural Networks: An Information-Theoretic Approach to Intentionality
• Ariel-ML: Computing Parallelization with Embedded Rust for Neural Networks on Heterogeneous Multi-core Microcontrollers
• CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities
• Representation Invariance and Allocation: When Subgroup Balance Matters
• Adaptive Federated Learning in Resource Constrained Edge Computing Systems
• Connectionist-Symbolic Machine Intelligence using Cellular Automata based Reservoir-Hyperdimensional Computing
• MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation
• Adaptive Regularized Newton Method with Inexact Hessian
• Densely Connected Convolutional Networks
• Fully Decentralized Certified Unlearning
• Beyond Wave Variables: A Data-Driven Ensemble Approach for Enhanced Teleoperation Transparency and Stability
• GeoDM: Geometry-aware Distribution Matching for Dataset Distillation
• PR-CapsNet: Pseudo-Riemannian Capsule Network with Adaptive Curvature Routing for Graph Learning
• Learning by Minimizing the Sum of Ranked Range
• Fully Convolutional Neural Networks for Dynamic Object Detection in Grid Maps (Masters Thesis)
• Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks
• PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters
• Robust Super-Resolution GAN, with Manifold-based and Perception Loss
• Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
• Predicting Macroscopic Properties of Amorphous Monolayer Carbon via Pair Correlation Function
• Algorithm-hardware co-design of neuromorphic networks with dual memory pathways
• Barrier-Free Large-Scale Sparse Tensor Accelerator (BARISTA) For\n Convolutional Neural Networks
• Adaptive Structural Learning of Deep Belief Network for Medical Examination Data and Its Knowledge Extraction by using C4.5
• Rethinking the performance comparison between SNNS and ANNS
• PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning
• Geometric Prior-Guided Federated Prompt Calibration
• Sign-OPT: A Query-Efficient Hard-label Adversarial Attack
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry
• Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions
• Distributed attack detection scheme using deep learning approach for Internet of Things
• OverFeat: Integrated Recognition, Localization and Detection using\n Convolutional Networks
• CLUENet: Cluster Attention Makes Neural Networks Have Eyes
• Tensor object classification via multilinear discriminant analysis\n network
• Privacy Loss of Noise Perturbation via Concentration Analysis of A Product Measure
• Novel Deep Learning Architectures for Classification and Segmentation of Brain Tumors from MRI Images
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
• SPOOF: Simple Pixel Operations for Out-of-Distribution Fooling
• A Comparative Study on Synthetic Facial Data Generation Techniques for Face Recognition
• Decoding with Structured Awareness: Integrating Directional, Frequency-Spatial, and Structural Attention for Medical Image Segmentation
• Evaluation Framework for Centralized and Decentralized Aggregation Algorithm in Federated Systems
• Building a Telescope to Look Into High-Dimensional Image Spaces
• The Blueprints of Intelligence: A Functional-Topological Foundation for Perception and Representation
• CNN on `Top': In Search of Scalable &amp; Lightweight Image-based Jet Taggers
• TEINet: Towards an Efficient Architecture for Video Recognition
• Wasserstein Training of Boltzmann Machines
• DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks
• A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
• Neural Variability Enhances Artificial Network Robustness
• Generative Recursive Reasoning
• Adversarial Defense by Stratified Convolutional Sparse Coding
• BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning
• Gradual Domain Adaptation without Indexed Intermediate Domains
• Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification
• Mixture Proportion Estimation and PU Learning: A Modern Approach
• Practical and Light-weight Secure Aggregation for Federated Submodel Learning
• Fully Unsupervised Diversity Denoising with Convolutional Variational\n Autoencoders
• A Comprehensive Survey of Machine Learning Applied to Radar Signal Processing
• Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D U-Net
• A Cascaded Zoom-In Network for Patterned Fabric Defect Detection
• Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval
• Domain Feature Collapse: Implications for Out-of-Distribution Detection and Solutions
• Efficient Public Verification of Private ML via Regularization
• Density-Informed VAE (DiVAE): Reliable Log-Prior Probability via Density Alignment Regularization
• LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modeling
• Multi-Scale Visual Prompting for Lightweight Small-Image Classification
• Unitary Evolution Recurrent Neural Networks
• Neural Ordinary Differential Equations
• HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restoration
• What does LIME really see in images?
• Decision Tree Embedding by Leaf-Means
• Adaptive Decentralized Federated Learning for Robust Optimization
• Diffusion-Prior Split Gibbs Sampling for Synthetic Aperture Radar Imaging under Incomplete Measurements
• G-PIFNN: A Generalizable Physics-informed Fourier Neural Network Framework for Electrical Circuits
• Associative Memory using Attribute-Specific Neuron Groups-1: Learning between Multiple Cue Balls
• Provably Safe Model Updates
• Unifying Sign and Magnitude for Optimizing Deep Vision Networks via ThermoLion
• Composite optimization for robust blind deconvolution
• All-optical spiking neurosynaptic networks with self-learning capabilities
• Neural Networks for Predicting Permeability Tensors of 2D Porous Media: Comparison of Convolution- and Transformer-based Architectures
• Deep Learning for Generic Object Detection: A Survey
• Deep learning in neural networks: An overview
• A systematic study of the class imbalance problem in convolutional neural networks
• A survey on modern trainable activation functions
• Deep learning for symbols detection and classification in engineering drawings
• OoDAnalyzer: Interactive Analysis of Out-of-Distribution Samples
• A Universal Representation Transformer Layer for Few-Shot Image Classification
• Compact representations of convolutional neural networks via weight\n pruning and quantization
• A new rotating machinery fault diagnosis method based on the Time Series Transformer
• Domain Impression: A Source Data Free Domain Adaptation Method
• An Introduction to Convolutional Neural Networks
• milearn: A Python Package for Multi-Instance Machine Learning
• Synthetic Data and Artificial Neural Networks for Natural Scene Text\n Recognition
• Nonnegative autoencoder with simplified random neural network
• Learning from Between-class Examples for Deep Sound Recognition
• Reweighted Expectation Maximization
• Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges
• Towards Object Detection from Motion
• From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
• Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation
• Object-Centric Data Synthesis for Category-level Object Detection
• Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation
• Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
• Learning Discriminative Representation with Signed Laplacian Restricted\n Boltzmann Machine
• Fine-Grained Analysis of Optimization and Generalization for\n Overparameterized Two-Layer Neural Networks
• ByteStorm: a multi-step data-driven approach for Tropical Cyclones detection and tracking
• CyCNN: A Rotation Invariant CNN using Polar Mapping and Cylindrical Convolution Layers
• Evaluation of Similarity-based Explanations
• Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers
• Optical diffraction neural networks assisted computational ghost imaging through dynamic scattering media
• Fast ConvNets Using Group-wise Brain Damage
• Adapting the Function Approximation Architecture in Online Reinforcement\n Learning
• Consistency Regularization for Certified Robustness of Smoothed\n Classifiers
• Escaping Barren Plateaus in Variational Quantum Algorithms Using Negative Learning Rate in Quantum Internet of Things
• CORGI: GNNs with Convolutional Residual Global Interactions for Lagrangian Simulation
• An Improved and Generalised Analysis for Spectral Clustering
• A Trainable Centrality Framework for Modern Data
• Closing the Generalization Gap in Parameter-efficient Federated Edge Learning
• A3T-GCN for FTSE100 Components Price Forecasting
• Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization
• Input-Aware Dynamic Backdoor Attack
• The Multiclass Score-Oriented Loss (MultiSOL) on the Simplex
• Scalable Gaussian Processes for Supervised Hashing
• Likelihood Assignment for Out-of-Distribution Inputs in Deep Generative Models is Sensitive to Prior Distribution Choice
• Neuro-Inspired Visual Pattern Recognition via Biological Reservoir Computing
• A multi-task convolutional neural network for mega-city analysis using very high resolution satellite imagery and geospatial data
• Attention-based Deep Multiple Instance Learning
• Attention-Based Guided Structured Sparsity of Deep Neural Networks
• Object Recognition Using Deep Neural Networks: A Survey
• HarmonicAttack: An Adaptive Cross-Domain Audio Watermark Removal
• Deep Learning for Environmentally Robust Speech Recognition: An Overview of Recent Developments
• Sum-Product-Attention Networks: Leveraging Self-Attention in Probabilistic Circuits
• A Physics-Informed U-net-LSTM Network for Data-Driven Seismic Response Modeling of Structures
• On the One-sided Convergence of Adam-type Algorithms in Non-convex Non-concave Min-max Optimization
• FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning
• Understanding Convolutional Neural Networks
• Compressed Sensing using Generative Models
• Pruning and Quantization for Deep Neural Network Acceleration: A Survey
• Reservoir Transformers
• Variational bagging: a robust approach for Bayesian uncertainty quantification
• PaTAS: A Parallel System for Trust Propagation in Neural Networks Using Subjective Logic
• On the (Statistical) Detection of Adversarial Examples
• Automating Crystal-Structure Phase Mapping: Combining Deep Learning with Constraint Reasoning
• ShelfRectNet: Single View Shelf Image Rectification with Homography Estimation
• Advancing Image Classification with Discrete Diffusion Classification Modeling
• Multi-Person Pose Estimation with Enhanced Channel-wise and Spatial Information
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• MambaEye: A Size-Agnostic Visual Encoder with Causal Sequential Processing
• Advances and Challenges in Solar Flare Prediction: A Review
• Mitigating Backdoor Attacks in Federated Learning
• Deep Learning in Computer-Aided Diagnosis and Treatment of Tumors: A Survey
• Your Noise, My Signal: Exploiting Switching Noise for Stealthy Data Exfiltration from Desktop Computers
• Leveraging Unlabeled Scans for NCCT Image Segmentation in Early Stroke Diagnosis: A Semi-Supervised GAN Approach
• In Defense of LSTMs for Addressing Multiple Instance Learning Problems
• Decoupled Neural Interfaces using Synthetic Gradients
• Distributed Deep Neural Networks over the Cloud, the Edge and End Devices
• Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks
• Visual Imitation Made Easy
• Dynamic Granularity Matters: Rethinking Vision Transformers Beyond Fixed Patch Splitting
• DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
• Bayesian Incremental Learning for Deep Neural Networks
• Model-Free Information Extraction in Enriched Nonlinear Phase-Space
• A Sufficient Condition for Convergences of Adam and RMSProp
• FedSKETCH: Communication-Efficient and Private Federated Learning via Sketching
• Mitigating Architectural Mismatch During the Evolutionary Synthesis of\n Deep Neural Networks
• Cognitive Alpha Mining via LLM-Driven Code-Based Evolution
• Re-Key-Free, Risky-Free: Adaptable Model Usage Control
• Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic
• Dendritic Convolution for Noise Image Recognition
• A Unified Convergence Analysis for Shuffling-Type Gradient Methods
• Robust Adversarial Learning via Sparsifying Front Ends
• Cross-individual Recognition of Emotions by a Dynamic Entropy based on Pattern Learning with EEG features
• Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems
• Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
• Developing an AI Course for Synthetic Chemistry Students
• Revisiting hard thresholding for DNN pruning
• Mitigating Catastrophic Forgetting in Streaming Generative and Predictive Learning via Stateful Replay
• Using MLIR Transform to Design Sliced Convolution Algorithm
• Probing Antiferromagnetic Hysteresis on Programmable Quantum Annealers
• SG-OIF: A Stability-Guided Online Influence Framework for Reliable Vision Data
• Self-Supervised Learning by Curvature Alignment
• MemIntelli: A Generic End-to-End Simulation Framework for Memristive Intelligent Computing
• Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimization
• Deep Learning Analysis of Ions Accelerated at Shocks
• Bit Fusion: Bit-Level Dynamically Composable Architecture for\n Accelerating Deep Neural Networks
• Augmented Sliced Wasserstein Distances
• DelTriC: A Novel Clustering Method with Accurate Outlier
• Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets
• Dendrite Net: A White-Box Module for Classification, Regression, and System Identification
• Uncertainty-guided Model Generalization to Unseen Domains
• Three Mechanisms of Weight Decay Regularization
• Visual Interpretability for Deep Learning: a Survey
• Dynamic Transfer for Multi-Source Domain Adaptation
• Self-Supervised Adversarial Example Detection by Disentangled Representation
• Blocking Transferability of Adversarial Examples in Black-Box Learning Systems
• Ro-SOS: Metric Expression Network (MEnet) for Robust Salient Object Segmentation
• Shallow neural network yields regularization for ill-posed inverse problems
• An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning
• Learning without Forgetting
• Scenario-Aware Control of Segmented Ladder Bus: Design and FPGA Implementation
• Learning Hierarchical Priors in VAEs
• ModelPred: A Framework for Predicting Trained Model from Training Data
• Very Deep Multilingual Convolutional Neural Networks for LVCSR
• On Large-Batch Training for Deep Learning: Generalization Gap and Sharp\n Minima
• Pharmacophore-based design by learning on voxel grids
• A Review of Machine Learning for Cavitation Intensity Recognition in Complex Industrial Systems
• Arc Detection and Recognition in the Pantograph-Catenary System Based on Multi-Information Fusion
• Recognition in Terra Incognita
• Continual Learning with Deep Generative Replay
• Bounds for Vector-Valued Function Estimation
• Matrix Neural Networks
• Decontamination of Mutual Contamination Models
• Deep learning for improved global precipitation in numerical weather prediction systems
• Hyper-VIB: A Hypernetwork-Enhanced Information Bottleneck Approach for Task-Oriented Communications
• Transferable Dual-Domain Feature Importance Attack against AI-Generated Image Detector
• FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning
• Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer
• Feedback U-net for Cell Image Segmentation
• Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?
• DeepPicker: a Deep Learning Approach for Fully Automated Particle Picking in Cryo-EM
• Provably Consistent Partial-Label Learning
• Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
• Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification
• Power Homotopy for Zeroth-Order Non-Convex Optimizations
• Extreme Aerodynamics: A Data-Driven Perspective
• Fast and Robust Simulation-Based Inference With Optimization Monte Carlo
• SATNet: Bridging deep learning and logical reasoning using a\n differentiable satisfiability solver
• Factorized Gaussian Process Variational Autoencoders
• Rethinking Data Value: Asymmetric Data Shapley for Structure-Aware Valuation in Data Markets and Machine Learning Pipelines
• H-CNN-ViT: A Hierarchical Gated Attention Multi-Branch Model for Bladder Cancer Recurrence Prediction
• Online Batch Selection for Faster Training of Neural Networks
• High Accuracy and High Fidelity Extraction of Neural Networks
• Efficient Processing of Deep Neural Networks: A Tutorial and Survey
• Multiple Source Domain Adaptation with Adversarial Training of Neural\n Networks
• Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• Lifelong Mixture of Variational Autoencoders
• A Methodology for Automatic Selection of Activation Functions to Design Hybrid Deep Neural Networks
• Sequence to Sequence Learning with Neural Networks
• On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty
• BinaryConnect: Training Deep Neural Networks with binary weights during propagations
• Defining Energy Indicators for Impact Identification on Aerospace Composites: A Physics-Informed Machine Learning Perspective
• Questions to Guide the Future of Artificial Intelligence Research
• Pointwise Convolutional Neural Networks
• Improving Network Robustness against Adversarial Attacks with Compact Convolution
• Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
• Deep Learning in Wide-field Surveys: Fast Analysis of Strong Lenses in Ground-based Cosmic Experiments
• Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior
• The Limitations of Model Uncertainty in Adversarial Settings
• HFNO: an interpretable data-driven decomposition strategy for turbulent flows
• Domain Generalization via Inference-time Label-Preserving Target Projections
• Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
• Video Swin Transformer
• A Survey on Green Deep Learning
• Alpha-Integration Pooling for Convolutional Neural Networks
• Prioritized Experience Replay
• How to Evaluate Machine Learning Approaches for Combinatorial Optimization: Application to the Travelling Salesman Problem
• Genetic Programming and Gradient Descent: A Memetic Approach to Binary Image Classification
• Plasmodium Detection Using Simple CNN and Clustered GLCM Features
• Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation
• Understanding the Interaction of Adversarial Training with Noisy Labels
• LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks
• MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance
• Towards Interaction Detection Using Topological Analysis on Neural Networks
• Incentives for Federated Learning: a Hypothesis Elicitation Approach
• Memory-Associated Differential Learning
• Gated Graph Sequence Neural Networks
• Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifolds
• Complex-to-Real Sketches for Tensor Products with Applications to the Polynomial Kernel
• Omni-GAN: On the Secrets of cGANs and Beyond
• HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients
• A Probabilistic Approach to Neural Network Pruning
• Dynamic Network Surgery for Efficient DNNs
• Sub-Seasonal Climate Forecasting via Machine Learning: Challenges, Analysis, and Advances
• Counterfactual Visual Explanations
• Credit scoring using neural networks and SURE posterior probability calibration
• Neural Architecture Search with Reinforcement Learning
• Glance-and-Gaze Vision Transformer
• Recent Advances in Convolutional Neural Networks
• Discovery and Separation of Features for Invariant Representation Learning
• Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services
• Accelerating Robustness Verification of Deep Neural Networks Guided by Target Labels
• Dynamic Computational Time for Visual Attention
• Label-Only Membership Inference Attacks
• Deep Random Forest with Ferroelectric Analog Content Addressable Memory
• A Progressive Batching L-BFGS Method for Machine Learning
• Search Intelligence: Deep Learning For Dominant Category Prediction
• Credit Assignment Through Broadcasting a Global Error Vector
• Structured Dropout Variational Inference for Bayesian Neural Networks
• Shifted Chunk Transformer for Spatio-Temporal Representational Learning
• On Anytime Learning at Macroscale
• Model Patching: Closing the Subgroup Performance Gap with Data Augmentation
• Semantic Change Detection with Hypermaps
• Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
• Dense neural networks as sparse graphs and the lightning initialization
• Robust Deep Neural Networks Inspired by Fuzzy Logic
• MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery
• HexCNN: A Framework for Native Hexagonal Convolutional Neural Networks
• Controlling generative models with continuous factors of variations
• Improving Query Efficiency of Black-box Adversarial Attack
• A Multicollinearity-Aware Signal-Processing Framework for Cross-β Identification via X-ray Scattering of Alzheimer's Tissue
• Rethinking Experience Replay: a Bag of Tricks for Continual Learning
• LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment
• CEDL: Centre-Enhanced Discriminative Learning for Anomaly Detection
• Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?
• Intelligent Collaborative Optimization for Rubber Tyre Film Production Based on Multi-path Differentiated Clipping Proximal Policy Optimization
• To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance
• Volatility in Certainty (VC): A Metric for Detecting Adversarial Perturbations During Inference in Neural Network Classifiers
• TopoPerception: A Shortcut-Free Evaluation of Global Visual Perception in Large Vision-Language Models
• Protecting the Neural Networks against FGSM Attack Using Machine Unlearning
• Tight Robustness Certification through the Convex Hull of ℓ₀ Attacks
• On the Detectability of Active Gradient Inversion Attacks in Federated Learning
• Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
• Multi-step Predictive Coding Leads To Simplicity Bias
• Tighter Truncated Rectangular Prism Approximation for RNN Robustness Verification
• Improving VisNet for Object Recognition
• Improve Contrastive Clustering Performance by Multiple Fusing-Augmenting ViT Blocks
• Training Aware Sigmoidal Optimizer
• Rate-Regularization and Generalization in VAEs
• DaST: Data-free Substitute Training for Adversarial Attacks
• Scaling the Convex Barrier with Sparse Dual Algorithms
• DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
• Fibre integrated circuits by a multilayered spiral architecture
• Reliable Fidelity and Diversity Metrics for Generative Models
• AutoFL: Enabling Heterogeneity-Aware Energy Efficient Federated Learning
• Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks
• Holdout SGD: Byzantine Tolerant Federated Learning
• Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
• Semi-Conditional Normalizing Flows for Semi-Supervised Learning
• Parallel and distributed asynchronous adaptive stochastic gradient methods
• Chargrid: Towards Understanding 2D Documents
• Rethinking Explanation Evaluation under the Retraining Scheme
• Distributed Zero-Shot Learning for Visual Recognition
• Multi-Objective Bilevel Learning
• Schedulers for Schedule-free: Theoretically inspired hyperparameters
• Misaligned by Design: Incentive Failures in Machine Learning
• Enhancing Binary Encoded Crime Linkage Analysis Using Siamese Network
• Impacts of the Numbers of Colors and Shapes on Outlier Detection: from Automated to User Evaluation
• Integrating Large Circular Kernels into CNNs through Neural Architecture Search
• Scalable Unidirectional Pareto Optimality for Multi-Task Learning with\n Constraints
• Pixel Recurrent Neural Networks
• Representation Learning: A Review and New Perspectives
• Revisiting the Neural Tangent Kernel: the role of large width and depth
• Adversarial Feature Learning
• Harnessing Sparsification in Federated Learning: A Secure, Efficient, and Differentially Private Realization
• AuxBlocks: Defense Adversarial Example via Auxiliary Blocks
• Sampling and Loss Weights in Multi-Domain Training
• A Hybrid Autoencoder-Transformer Model for Robust Day-Ahead Electricity Price Forecasting under Extreme Conditions
• Classification and Segmentation of Pulmonary Lesions in CT Images Using\n a Combined VGG-XGBoost Method, and an Integrated Fuzzy Clustering-Level Set\n Technique
• Beyond Uniform Deletion: A Data Value-Weighted Framework for Certified Machine Unlearning
• Fix Your Features: Stationary and Maximally Discriminative Embeddings using Regular Polytope (Fixed Classifier) Networks
• Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
• Convolution in Convolution for Network in Network
• Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks
• Representation Quality Of Neural Networks Links To Adversarial Attacks and Defences
• Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning
• SMiLE: Provably Enforcing Global Relational Properties in Neural Networks
• Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization
• DeepBooTS: Dual-Stream Residual Boosting for Drift-Resilient Time-Series Forecasting
• TextBoxes: A Fast Text Detector with a Single Deep Neural Network
• Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
• Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data
• Equilibrated Recurrent Neural Network: Neuronal Time-Delayed Self-Feedback Improves Accuracy and Stability
• Robust Visual Tracking via Convolutional Networks
• Learning Topology-Driven Multi-Subspace Fusion for Grassmannian Deep Network
• Robust Nearest Neighbour Retrieval Using Targeted Manifold Manipulation
• QDCNN: Quantum Dilated Convolutional Neural Network
• Multivariate Variational Autoencoder
• On the Expressive Power of Deep Neural Networks
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• Auto-Keras: An Efficient Neural Architecture Search System
• Benchmark Designers Should "Train on the Test Set" to Expose Exploitable Non-Visual Shortcuts
• TT-Prune: Joint Model Pruning and Resource Allocation for Communication-efficient Time-triggered Federated Learning
• Twirlator: A Pipeline for Analyzing Subgroup Symmetry Effects in Quantum Machine Learning Ansatzes
• Dynamical regimes of diffusion models
• A Hybrid CNN-Cheby-KAN Framework for Efficient Prediction of Two-Dimensional Airfoil Pressure Distribution
• 3D Cal: An Open-Source Software Library for Calibrating Tactile Sensors
• Fast Gradient-Based Inference with Continuous Latent Variable Models in Auxiliary Form
• Explaining Deep Learning Models using Causal Inference
• A novel method for identifying the deep neural network model with the Serial Number
• On Complex Valued Convolutional Neural Networks
• Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
• Detecting cutaneous basal cell carcinomas in ultra-high resolution and weakly labelled histopathological images
• Just Least Squares: Binary Compressive Sampling with Low Generative Intrinsic Dimension
• Unlocking the archives: Using large language models to transcribe handwritten historical documents
• Convolutional Neural Networks for classifying galaxy mergers: Can faint tidal features aid in classifying mergers?
• Discovering indicators of dark horse of soccer games by deep learning from sequential trading data
• Efficient Detection and Characterization of Targets of Natural Selection Using Transfer Learning
• Benchmark-Ready 3D Anatomical Shape Classification
• Enhancing Federated Learning Privacy with QUBO
• Generalizable super-resolution turbulence reconstruction from minimal training data
• SigmaCollab: An Application-Driven Dataset for Physically Situated Collaboration
• Neural network initialization with nonlinear characteristics and information on hierarchical features
• PrivGNN: High-Performance Secure Inference for Cryptographic Graph Neural Networks
• Random Initialization of Gated Sparse Adapters
• Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering
• Bayesian Coreset Optimization for Personalized Federated Learning
• SpEx: A Spectral Approach to Explainable Clustering
• A Hybrid YOLOv5-SSD IoT-Based Animal Detection System for Durian Plantation Protection
• TRISKELION-1: Unified Descriptive-Predictive-Generative AI
• Feedback alignment in deep convolutional networks
• Exploring Landscapes for Better Minima along Valleys
• Integrating ConvNeXt and Vision Transformers for Enhancing Facial Age Estimation
• Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules
• Running VLAs at Real-time Speed
• On Measuring Localization of Shortcuts in Deep Networks
• Higher-Order Regularization Learning on Hypergraphs
• Machine learning-based upscaling of rock permeability from pore scale to core scale: effect of training dataset size and sub-core volumes
• Accumulative SGD Influence Estimation for Data Attribution
• Detecting Anomalies in Machine Learning Infrastructure via Hardware Telemetry
• Coherence-Aware Distributed Learning under Heterogeneous Downlink Impairments
• Imbalanced Continual Learning with Partitioning Reservoir Sampling
• Weighed l1 on the simplex: Compressive sensing meets locality
• Convex variational methods for multiclass data segmentation on graphs
• A Convexity-dependent Two-Phase Training Algorithm for Deep Neural Networks
• Lightweight Federated Learning in Mobile Edge Computing with Statistical and Device Heterogeneity Awareness
• Variance-Preserving Orthogonal Selection (VPOS): Greedy Feature Selection via Orthogonal Deflation in PCA Loading Space
• Can neural networks learn persistent homology features?
• Ensemble Federated Adversarial Training with Non-IID data
• Deep Learning Algorithms with Applications to Video Analytics for A Smart City: A Survey
• Latent Space Non-Linear Statistics
• Variational Dropout Sparsifies Deep Neural Networks
• Spatially-Adaptive Filter Units for Deep Neural Networks
• Deep Learning for Anomaly Detection: A Review
• A ConvNet for the 2020s
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Learning to Refine Object Segments
• Understanding Information Processing in Human Brain by Interpreting Machine Learning Models
• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
• To Create What You Tell: Generating Videos from Captions
• Fast Convergence of DETR with Spatially Modulated Co-Attention
• Hire-MLP: Vision MLP via Hierarchical Rearrangement
• Detecting GAN-generated Imagery using Color Cues
• Client-Edge-Cloud Hierarchical Federated Learning
• CNN depth analysis with different channel inputs for Acoustic Scene Classification
• Deep Compressive Macroscopic Fluorescence Lifetime Imaging
• End-to-end Deep Learning from Raw Sensor Data: Atrial Fibrillation\n Detection using Wearables
• Identifying Untrustworthy Predictions in Neural Networks by Geometric\n Gradient Analysis
• Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation
• Predictive Uncertainty Estimation via Prior Networks
• Lipschitz constant estimation of Neural Networks via sparse polynomial optimization
• Deep High-Resolution Representation Learning for Visual Recognition
• Heuristic methods and performance bounds for photonic design
• Intrinsic dimension estimation of data by principal component analysis
• Learning Similarity for Character Recognition and 3D Object Recognition
• Topological Deep Learning
• Domain Adaptation Meets Disentangled Representation Learning and Style Transfer
• Regularizing Explanations in Bayesian Convolutional Neural Networks
• Understanding Attention and Generalization in Graph Neural Networks
• Density Estimation for Geolocation via Convolutional Mixture Density Network
• Towards co-evolution of fitness predictors and Deep Neural Networks
• Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases
• Federated Learning Based on Dynamic Regularization
• Conditional Deep Learning for Energy-Efficient and Enhanced Pattern\n Recognition
• Distance-Based Regularisation of Deep Networks for Fine-Tuning
• Efficient and Less Centralized Federated Learning
• A hierarchical framework for object recognition
• Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
• Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark
• Do Deep Neural Networks Suffer from Crowding?
• Predicting Mild Cognitive Impairment to Alzheimer's Disease Progression by Explainable Multi‐Modal Framework Using Deep and Machine Learning Hybrid Model
• N-GCN: Multi-scale Graph Convolution for Semi-supervised Node\n Classification
• Provable limitations of deep learning
• Greedy Strategy Works for k-Center Clustering with Outliers and Coreset Construction
• Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation
• Deep Rotation Equivariant Network
• Open Compound Domain Adaptation
• Towards stability and optimality in stochastic gradient descent
• A Note on Deepfake Detection with Low-Resources
• Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
• Active Divergence with Generative Deep Learning -- A Survey and Taxonomy
• Computer vision for high-throughput materials synthesis: a tutorial for experimentalists
• Grounding large language models in an anthropological knowledge graph: A neuro-symbolic approach
• Neurodatascience: Past, Present, and Future
• A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton
• Few-Shot Object Recognition from Machine-Labeled Web Images
• Verification of Neural Networks: Enhancing Scalability through Pruning
• Deep learning based fence segmentation and removal from an image using a\n video sequence
• Normalized Flat Minima: Exploring Scale Invariant Definition of Flat\n Minima for Neural Networks using PAC-Bayesian Analysis
• NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
• Ternary Weight Networks
• A Low Power In-Memory Multiplication andAccumulation Array with Modified Radix-4 Inputand Canonical Signed Digit Weights
• Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets
• APE-GAN: Adversarial Perturbation Elimination with GAN
• Learning Identity-Preserving Transformations on Data Manifolds
• Training Models to Extract Treatment Plans from Clinical Notes Using Contents of Sections with Headings
• Concept Drift and Covariate Shift Detection Ensemble with Lagged Labels
• Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
• Survey: Transformer based Video-Language Pre-training
• An Introduction to Image Synthesis with Generative Adversarial Nets
• Covert Model Poisoning Against Federated Learning: Algorithm Design and Optimization
• Chargrid-OCR: End-to-end Trainable Optical Character Recognition for Printed Documents using Instance Segmentation
• On the Equivalence of Convolutional and Hadamard Networks using DFT
• Places: An Image Database for Deep Scene Understanding
• Training generative neural networks via Maximum Mean Discrepancy optimization
• Wasserstein Auto-Encoders
• Automatic Symmetry Discovery with Lie Algebra Convolutional Network
• Over-Sampling in a Deep Neural Network
• Object Detection in 20 Years: A Survey
• Training Deep Spiking Auto-encoders without Bursting or Dying Neurons through Regularization
• Cnns in land cover mapping with remote sensing imagery: a review and meta-analysis
• A Survey on Methods and Theories of Quantized Neural Networks
• On the Effects of Quantisation on Model Uncertainty in Bayesian Neural Networks
• Bayesian Neural Networks at Finite Temperature
• Performance Guaranteed Network Acceleration via High-Order Residual Quantization
• Category decoding of visual stimuli from human brain activity using a bidirectional recurrent neural network to simulate bidirectional information flows in human visual cortices
• Text Flow: A Unified Text Detection System in Natural Scene Images
• Deep learning generalizes because the parameter-function map is biased towards simple functions
• Follow the bisector: a simple method for multi-objective optimization
• Understanding and Diagnosing Vulnerability under Adversarial Attacks
• Conditional Time Series Forecasting with Convolutional Neural Networks
• A Free-Energy Principle for Representation Learning
• Active Learning Using Uncertainty Information
• Known-plaintext attack and ciphertext-only attack for encrypted single-pixel imaging
• A Novel Framework for Selection of GANs for an Application
• SNIPER: Efficient Multi-Scale Training
• Towards All-around Knowledge Transferring: Learning From Task-irrelevant Labels
• Combating Adversarial Attacks Using Sparse Representations
• Extracting informative vortical structures of turbulent wake-extreme vortex gust interactions with machine learning
• Mitigating Sybils in Federated Learning Poisoning
• Robust Hypothesis Testing Using Wasserstein Uncertainty Sets
• Explicit Disentanglement of Appearance and Perspective in Generative\n Models
• Facial Key Points Detection using Deep Convolutional Neural Network - NaimishNet
• FloDR: An invertible dimensionality reduction method based on a normalising flow
• Distributed Optimization for Over-Parameterized Learning
• Learning Spatial Relationships between Samples of Patent Image Shapes
• Exploiting the Potential of Standard Convolutional Autoencoders for\n Image Restoration by Evolutionary Search
• Adversarial Attacks on Binary Image Recognition Systems
• ChipNet: Budget-Aware Pruning with Heaviside Continuous Approximations
• Doubly Stochastic Subspace Clustering
• Predicting the near-wall region of turbulence through convolutional neural networks
• Compressed Learning: A Deep Neural Network Approach
• Noisy Batch Active Learning with Deterministic Annealing
• The Weighted Euler Curve Transform for Shape and Image Analysis
• Kernel-Guided Training of Implicit Generative Models with Stability Guarantees
• Federated Mixture of Experts
• Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases
• Train-by-Reconnect: Decoupling Locations of Weights from their Values
• Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty
• The data center of tomorrow is made up of heterogeneous accelerators
• Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit
• DeepIris: Iris Recognition Using A Deep Learning Approach
• Positive-Unlabeled Learning with Non-Negative Risk Estimator
• Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification
• <scp>RIBM3DU‐Net</scp>: Glioma tumour substructures segmentation in magnetic resonance images using residual‐inception block with modified <scp>3D U‐Net</scp> architecture
• <scp>CasUNeXt</scp>: A Cascaded Transformer With Intra‐ and Inter‐Scale Information for Medical Image Segmentation
• Skeleton-Based Action Recognition With Gated Convolutional Neural Networks
• Image Captioning and Visual Question Answering Based on Attributes and External Knowledge
• The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
• Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing
• Machine learning on sequential data using a recurrent weighted average
• Steganography With Constructing Neural Networks
• Deep Unsupervised Clustering Using Mixture of Autoencoders
• Overcoming Forgetting in Federated Learning on Non-IID Data
• Comparing Rule-Based and Deep Learning Models for Patient Phenotyping
• Fold bifurcation identification through scientific machine learning
• Relational Self-Attention: What's Missing in Attention for Video Understanding
• On Calibration of Modern Neural Networks
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• An Efficient Adversarial Attack for Tree Ensembles
• Drop-DTW: Aligning Common Signal Between Sequences While Dropping Outliers
• Edge-Cloud Collaborated Object Detection via Difficult-Case Discriminator
• Reusable weights initialization framework of neural networks for function approximation
• Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
• Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
• Theano-based Large-Scale Visual Recognition with Multiple GPUs
• Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
• Online Variance Reduction for Stochastic Optimization
• Deep clustering with concrete k-means
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Convolutional Neural Networks for Sentence Classification
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Few-shot Learning by Exploiting Visual Concepts within CNNs
• An Information Theory-inspired Strategy for Automatic Network Pruning
• The Tree Ensemble Layer: Differentiability meets Conditional Computation
• Collaborating Foundation Models for Domain Generalized Semantic Segmentation
• BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
• Classification of Pathological and Normal Gait: A Survey
• Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
• DROCC: Deep Robust One-Class Classification
• Online Learning with Gated Linear Networks
• Quantized Adam with Error Feedback
• Towards Book Cover Design via Layout Graphs
• A Saak Transform Approach to Efficient, Scalable and Robust Handwritten Digits Recognition
• Wandering Within a World: Online Contextualized Few-Shot Learning
• ExKMC: Expanding Explainable k-Means Clustering
• Machine Learning Etudes in Conformal Field Theories
• Interpretable Deep Convolutional Fuzzy Classifier
• SWNet: Small-World Neural Networks and Rapid Convergence
• L4: Practical loss-based stepsize adaptation for deep learning
• Towards Understanding the Generalization Bias of Two Layer Convolutional Linear Classifiers with Gradient Descent
• Efficient Privacy-Preserving Stochastic Nonconvex Optimization
• B-CNN: Branch Convolutional Neural Network for Hierarchical Classification
• Quantal synaptic dilution enhances sparse encoding and dropout regularisation in deep networks
• GP-VAE: Deep Probabilistic Time Series Imputation
• Metaethical perspectives on ‘benchmarking’ AI ethics
• Conditional Neural Processes
• Demystifying MMD GANs
• Minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity
• Learning Comment Generation by Leveraging User-Generated Data
• Modulated binary cliquenet
• Controlling Recurrent Neural Networks by Conceptors
• Benefits of depth in neural networks
• Cross-domain Few-shot Learning with Task-specific Adapters
• Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation
• Compatible Learning for Deep Photonic Neural Network
• Two-stream Flow-guided Convolutional Attention Networks for Action Recognition
• Federated Learning on Non-IID Data Silos: An Experimental Study
• Adversarial confidence and smoothness regularizations for scalable unsupervised discriminative learning
• Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
• A guide for Single Particle Tracking: from sample preparation and image acquisition to the analysis of individual trajectories
• Shot-based quantum encoding: a data-loading paradigm for quantum neural networks
• Neural Spline Flows
• Mitigating Bias in Calibration Error Estimation
• Increasing Depth Leads to U-Shaped Test Risk in Over-parameterized\n Convolutional Networks
• Stable Tensor Neural Networks for Rapid Deep Learning
• Efficient Sparse-Winograd Convolutional Neural Networks
• Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets
• On the Vulnerability of Capsule Networks to Adversarial Attacks
• Strategies for Conceptual Change in Convolutional Neural Networks
• Modern <scp>machine‐learning</scp> for binding affinity estimation of <scp>protein–ligand</scp> complexes: Progress, opportunities, and challenges
• A Petri Dish for Histopathology Image Analysis
• Towards Robust, Locally Linear Deep Networks
• Pruning at a Glance: Global Neural Pruning for Model Compression
• Transform-Invariant Convolutional Neural Networks for Image\n Classification and Search
• Learning Cross-domain Generalizable Features by Representation Disentanglement
• A Survey on Deep Learning Toolkits and Libraries for Intelligent User Interfaces
• Exploiting Deep Features for Remote Sensing Image Retrieval: A Systematic Investigation
• Likelihood-free MCMC with Amortized Approximate Ratio Estimators
• Differential Similarity in Higher Dimensional Spaces: Theory and Applications
• A two-stage deep learning framework for automated kidney stone detection in CT images
• Tokenization and deep learning architectures in genomics: A comprehensive review
• Intelligence Beyond the Edge: Inference on Intermittent Embedded Systems
• Gradient Estimation Using Stochastic Computation Graphs
• Post-processing enhances protein secondary structure prediction with second order deep learning and embeddings
• Novel Uncertainty Framework for Deep Learning Ensembles
• The ripple effect of dataset reuse: Contextualising the data lifecycle for machine learning data sets and social impact
• Optimal transport mapping via input convex neural networks
• Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes
• Neural Plasticity Networks
• Enhancing the performance of data-driven liquid loading severity grading models for shale gas wells using contrastive learning
• Calibrated Uncertainty Sampling for Active Learning
• Learning From Less Data: Diversified Subset Selection and Active\n Learning in Image Classification Tasks
• Stochastic Region Pooling: Make Attention More Expressive
• Improving Image Classification Robustness through Selective CNN-Filters Fine-Tuning
• Improving the Authentication with Built-in Camera Protocol Using\n Built-in Motion Sensors: A Deep Learning Solution
• Progressive Feature Alignment for Unsupervised Domain Adaptation
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Policy-GNN: Aggregation Optimization for Graph Neural Networks
• Signed Input Regularization
• Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
• Understanding the Impact of Quantization, Accuracy, and Radiation on the Reliability of Convolutional Neural Networks on FPGAs
• A Survey on Bayesian Deep Learning
• Automatic labeling of molecular biomarkers of whole slide immunohistochemistry images using fully convolutional networks
• A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
• How to Leverage Multimodal EHR Data for Better Medical Predictions?
• Super-Resolution with Deep Convolutional Sufficient Statistics
• Convolutional Networks for Image Processing by Coupled Oscillator Arrays
• Sequence Transduction with Recurrent Neural Networks
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks
• Deep Learning with Label Differential Privacy
• Learning Factorized Multimodal Representations
• FAT: Federated Adversarial Training
• Gradient descent revisited via an adaptive online learning rate
• Graph neural networks: A review of methods and applications
• Interpretable Text Classification Using CNN and Max-pooling
• Inhibited Softmax for Uncertainty Estimation in Neural Networks
• Inference Suboptimality in Variational Autoencoders
• Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
• To understand deep learning we need to understand kernel learning
• The Convolutional Tsetlin Machine
• Stateful Detection of Model Extraction Attacks
• A deep Convolutional Neural Network for topology optimization with strong generalization ability
• Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
• Facing the Electorate: Computational Approaches to the Study of Nonverbal Communication and Voter Impression Formation
• High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
• Acceleration of Deep Neural Network Training with Resistive Cross-Point Devices: Design Considerations
• Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
• Deep Metric Learning for Practical Person Re-Identification
• Enhancing Passive Non-Line-of-Sight Imaging via Dynamic Channel Optimization
• Peri-Net-Pro: The neural processes with quantified uncertainty for crack patterns
• An Image Patch is a Wave: Phase-Aware Vision MLP
• Deep Structural Causal Models for Tractable Counterfactual Inference
• Multivariate Time Series Classification using Dilated Convolutional Neural Network
• On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation
• Learning degraded image classification with restoration data fidelity
• An Image Dataset of Text Patches in Everyday Scenes
• RC2020 Report: Learning De-biased Representations with Biased Representations
• Applications of data augmentation in mineral prospectivity prediction based on convolutional neural networks
• Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering
• Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory
• Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks
• Random VLAD based Deep Hashing for Efficient Image Retrieval
• Guided Labeling using Convolutional Neural Networks
• On the Robustness of Interpretability Methods
• Filtrated Spectral Algebraic Subspace Clustering
• Learning Various Length Dependence by Dual Recurrent Neural Networks
• Adaptive Mixtures of Factor Analyzers
• Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations
• Adversarial Domain Adaptation with Domain Mixup
• Video Modeling with Correlation Networks
• Text Matching as Image Recognition
• An Acceleration Method Based on Deep Learning and Multilinear Feature\n Space
• Meta Feature Modulator for Long-tailed Recognition
• Lifted Regression/Reconstruction Networks
• Automatic Moth Detection from Trap Images for Pest Management
• The k-tied Normal Distribution: A Compact Parameterization of Gaussian\n Mean Field Posteriors in Bayesian Neural Networks
• Efficient Image Splicing Localization via Contrastive Feature Extraction
• UMAP-assisted K-means clustering of large-scale SARS-CoV-2 mutation datasets
• nnFormer: Volumetric Medical Image Segmentation via a 3D Transformer
• Bayesian Federated Learning over Wireless Networks
• Survey of the Detection and Classification of Pulmonary Lesions via CT and X-Ray
• On the Regret Minimization of Nonconvex Online Gradient Ascent for\n Online PCA
• High-resolution, yet statistically relevant, analysis of damage in DP steel using artificial intelligence
• Face Alignment Assisted by Head Pose Estimation
• Unlearnable Examples: Making Personal Data Unexploitable
• On the Origin of Deep Learning
• Stacked Hourglass Networks for Human Pose Estimation
• Learning with Group Invariant Features: A Kernel Perspective
• Streamlining Tensor and Network Pruning in PyTorch
• Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization
• Neural Networks with Activation Networks
• RepVGG: Making VGG-style ConvNets Great Again
• Pooling Hybrid Representations for Web Structured Data Annotation
• On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective
• Channel-Recurrent Autoencoding for Image Modeling
• Survey of Automated Vulnerability Detection and Exploit Generation\n Techniques in Cyber Reasoning Systems
• Training Stronger Baselines for Learning to Optimize
• Palmprint Recognition Using Deep Scattering Convolutional Network
• Infinite-dimensional Folded-in-time Deep Neural Networks
• Deep High-Resolution Representation Learning for Visual Recognition
• Discrete Event, Continuous Time RNNs
• Continual Learning in Recurrent Neural Networks
• Dynamic Feature Acquisition with Arbitrary Conditional Flows
• Towards Rapid and Robust Adversarial Training with One-Step Attacks
• GAL: Gradient Assisted Learning for Decentralized Multi-Organization Collaborations
• Content-Adaptive Pixel Discretization to Improve Model Robustness
• Deep Learning in Robotics: A Review of Recent Research
• Temporal Spike Sequence Learning via Backpropagation for Deep Spiking Neural Networks
• Federated Learning With Differential Privacy: Algorithms and Performance Analysis
• Dataset Meta-Learning from Kernel Ridge-Regression
• Post-Disturbance Dynamic Frequency Features Prediction Based on Convolutional Neural Network
• DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
• An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack
• Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks
• Fantastic Four: Differentiable Bounds on Singular Values of Convolution\n Layers
• GenURL: A General Framework for Unsupervised Representation Learning
• Learning Local Invariant Mahalanobis Distances
• Feedback Attention for Cell Image Segmentation
• Deep Hierarchical Classification for Category Prediction in E-commerce System
• Decision-based Universal Adversarial Attack
• A Robust Computing-in-Memory Macro With 2T1R1C Cells and Reused Capacitors for Successive-Approximation ADC
• Deeply-Supervised Nets
• Can Single Neurons Solve MNIST? The Computational Power of Biological Dendritic Trees
• In-depth Question classification using Convolutional Neural Networks
• ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and\n Uncovering Biases
• Dynamic Few-Shot Visual Learning without Forgetting
• Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
• Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey
• Convolutional Neural Network-based Topology Optimization (CNN-TO) By Estimating Sensitivity of Compliance from Material Distribution
• Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge
• Use it or Lose it: Selective Memory and Forgetting in a Perpetual Learning Machine
• Beyond Photo Realism for Domain Adaptation from Synthetic Data
• Fixation prediction with a combined model of bottom-up saliency and vanishing point
• SMIL: Multimodal Learning with Severely Missing Modality
• Random feedback weights support learning in deep neural networks
• NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks
• One Versus all for deep Neural Network Incertitude (OVNNI) quantification
• Topological Regularization for Dense Prediction
• GMAIR: Unsupervised Object Detection Based on Spatial Attention and Gaussian Mixture
• Efficient Design of Majority-Logic-Based Approximate Arithmetic Circuits
• An Information-Geometric Distance on the Space of Tasks
• Universality of deep convolutional neural networks
• On Generalization Bounds for Projective Clustering
• From Variational to Deterministic Autoencoders
• On Periodic Functions as Regularizers for Quantization of Neural Networks
• PixelTransformer: Sample Conditioned Signal Generation
• DRAW: A Recurrent Neural Network For Image Generation
• Bayesian Hierarchical Clustering with Exponential Family: Small-Variance Asymptotics and Reducibility
• CapsNet comparative performance evaluation for image classification
• P-CNN: Pose-based CNN Features for Action Recognition
• Adversarial-Learned Loss for Domain Adaptation
• Multimodal Generative Models for Compositional Representation Learning
• Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
• Characterizing and Avoiding Negative Transfer
• PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
• On the Certified Robustness for Ensemble Models and Beyond
• Deep Quaternion Features for Privacy Protection
• Robust Aggregation for Federated Learning
• Residual Gated Graph ConvNets
• Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• A Study on the Uncertainty of Convolutional Layers in Deep Neural Networks
• Early Stopping without a Validation Set
• 3D Dense Separated Convolution Module for Volumetric Image Analysis
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
• Real-world Mapping of Gaze Fixations Using Instance Segmentation for\n Road Construction Safety Applications
• Interpretable Convolutional Neural Networks via Feedforward Design
• Practical and Fast Momentum-Based Power Methods
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Morphological Network: How Far Can We Go with Morphological Neurons?
• MRI-Based Surgical Planning for Lumbar Spinal Stenosis
• A Single-Cycle MLP Classifier Using Analog MRAM-based Neurons and Synapses
• Topical Behavior Prediction from Massive Logs
• Heimdallr: Fingerprinting SD-WAN Control-Plane Architecture via Encrypted Control Traffic
• Introducing machine learning for power system operation support
• Unsupervised Deep Embedding for Clustering Analysis
• Involution: Inverting the Inherence of Convolution for Visual Recognition
• Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows
• A Hybrid Approach to Privacy-Preserving Federated Learning
• A Deep Learning Perspective on the Origin of Facial Expressions
• Guidelines for Experimental Algorithmics in Network Analysis
• Wavelet based edge feature enhancement for convolutional neural networks
• Zero-Shot Text-to-Image Generation
• Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey
• TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images
• Towards Characterizing Adversarial Defects of Deep Learning Software from the Lens of Uncertainty
• Adaptive Normalized Risk-Averting Training For Deep Neural Networks
• Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning
• Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
• Understanding Convolutional Neural Networks with Information Theory: An Initial Exploration
• UP2D: Uncertainty-aware Progressive Pseudo-label Denoising for Source-Free Domain Adaptive Medical Image Segmentation
• Sparse Network Inversion for Key Instance Detection in Multiple Instance Learning
• Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
• Soft Gradient Boosting Machine
• SESR: Single Image Super Resolution with Recursive Squeeze and Excitation Networks
• TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
• Representation Learning: A Review and New Perspectives
• Likelihood Landscapes: A Unifying Principle Behind Many Adversarial Defenses
• Simplified Stochastic Feedforward Neural Networks
• Feature-Guided Analysis of Neural Networks: A Replication Study
• Synergizing chemical and AI communities for advancing laboratories of the future
• A Unified Geometric Space Bridging AI Models and the Human Brain
• Derivation and Analysis of Fast Bilinear Algorithms for Convolution
• Online convex optimization for cumulative constraints
• PMSSC: Parallelizable multi-subset based self-expressive model for subspace clustering
• Differential Privacy: Gradient Leakage Attacks in Federated Learning Environments
• Do Convolutional Networks need to be Deep for Text Classification ?
• FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated\n Recurrent Neural Network
• ResNet: Enabling Deep Convolutional Neural Networks through Residual Learning
• Strengths and Limitations of Statistical and Dynamical Downscaling for the Representation of Compound Dry and Hot Events Over Spain
• Predicting global warming potential: A self-training and ensemble machine learning approach
• DNN Quantization with Attention
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop
• Disentangling Factors of Variation with Cycle-Consistent Variational\n Auto-Encoders
• Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps
• M2GCNet: Multi-Modal Graph Convolution Network for Precise Brain Tumor Segmentation Across Multiple MRI Sequences
• Dual Averaging is Surprisingly Effective for Deep Learning Optimization
• Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion
• Learning Graphical Models of Images, Videos and Their Spatial Transformations
• Learning Stable Group Invariant Representations with Convolutional Networks
• PySCIPOpt-ML: Embedding Trained Machine Learning Models into Mixed-Integer Programs
• Adversarial NLI: A New Benchmark for Natural Language Understanding
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Humanoid-inspired Causal Representation Learning for Domain Generalization
• GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling
• PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
• Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
• MOOD: Multi-level Out-of-distribution Detection
• The Benchmarking Epistemology: Construct Validity for Evaluating Machine Learning Models
• GR-RNN: Global-Context Residual Recurrent Neural Networks for Writer Identification
• Knocking-Heads Attention
• Intrusion Detection: Machine Learning Baseline Calculations for Image\n Classification
• Hankel Singular Value Regularization for Highly Compressible State Space Models
• Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions
• A Review of End-to-End Precipitation Prediction Using Remote Sensing Data: from Divination to Machine Learning
• What Do We Understand About Convolutional Networks?
• Deep learning-based COVID-19 pneumonia classification using chest CT images: model generalizability
• ThetA -- fast and robust clustering via a distance parameter
• Transformers from Compressed Representations
• Some aspects of neural network parameter optimization for joint inversion of gravitational and magnetic fields
• Deep Domain Adaptation under Deep Label Scarcity
• Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognition
• Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
• Low-Precision Streaming PCA
• Top-Down Semantic Refinement for Image Captioning
• GALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptation
• Deep Visual-Semantic Alignments for Generating Image Descriptions
• On Masked Pre-training and the Marginal Likelihood
• Power to the Clients: Federated Learning in a Dictatorship Setting
• Two Ridge Solutions for the Incremental Broad Learning System on Added Nodes
• Frequentist Validity of Epistemic Uncertainty Estimators
• Caption-Driven Explainability: Probing CNNs for Bias via CLIP
• Toolflows for Mapping Convolutional Neural Networks on FPGAs: A Survey and Future Directions
• A Systematic Collection of Medical Image Datasets for Deep Learning
• Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions
• Widening and Squeezing: Towards Accurate and Efficient QNNs
• Head Pursuit: Probing Attention Specialization in Multimodal Transformers
• EBOP MAVEN: A machine learning model to estimate the input parameters for analytic fitting of detached eclipsing binary light curves
• Model Merging with Functional Dual Anchors
• Active Learning: Problem Settings and Recent Developments
• Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks
• Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data
• Stand-Alone Self-Attention in Vision Models
• Domain Generalization with MixStyle
• Learning from a Lightweight Teacher for Efficient Knowledge Distillation
• Contribution of task-irrelevant stimuli to drift of neural representations
• MirrorFuzz: Leveraging LLM and Shared Bugs for Deep Learning Framework APIs Fuzzing
• H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition
• Adding Gradient Noise Improves Learning for Very Deep Networks
• Automatic structured variational inference
• Predicting the 3D microstructure of SOFC anodes from 2D SEM images using stochastic microstructure modeling and CNNs
• Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature
• Anderson-type acceleration method for Deep Neural Network optimization
• Local Propagation in Constraint-based Neural Network
• Recursive Feature Generation for Knowledge-based Learning
• Deep Discriminative Clustering Analysis
• Fluctuation-dissipation relations for stochastic gradient descent
• Unsupervised Transductive Domain Adaptation
• A Survey on Spoken Language Understanding: Recent Advances and New Frontiers
• Data-Adaptive Transformed Bilateral Tensor Low-Rank Representation for Clustering
• Comparison of Methods Generalizing Max- and Average-Pooling
• Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems
• Graph kernels between point clouds
• Pointwise Binary Classification with Pairwise Confidence Comparisons
• Optimization of the quantization of dense neural networks from an exact QUBO formulation
• Provably Convergent Algorithms for Solving Inverse Problems Using Generative Models
• Multi-source Distilling Domain Adaptation
• A Machine Learning Accelerator In-Memory for Energy Harvesting
• HAMLOCK: HArdware-Model LOgically Combined attacK
• Tibetan Language and AI: A Comprehensive Survey of Resources, Methods and Challenges
• Entity Embeddings of Categorical Variables
• Representation Learning with Multisets
• Cold Case: The Lost MNIST Digits
• Online Handwritten Signature Verification Based on Temporal-Spatial Graph Attention Transformer
• Layer-Parallel Training of Deep Residual Neural Networks
• Scalable LinUCB: Low-Rank Design Matrix Updates for Recommenders with Large Action Spaces
• Neural Variational Dropout Processes
• Matrix-Free Least Squares Solvers: Values, Gradients, and What to Do With Them
• DFCA: Decentralized Federated Clustering Algorithm
• Category learning in deep neural networks: Information content and geometry of internal representations
• On Biologically Plausible Learning in Continuous Time
• Psycholinguistic Tripartite Graph Network for Personality Detection
• WAFFLE: Watermarking in Federated Learning
• Function Contrastive Learning of Transferable Meta-Representations
• Identify Significant Phenomenon-Specific Variables for Multivariate Time Series
• PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classification
• Transferable Active Grasping and Real Embodied Dataset
• Deep Spiking Neural Networks with Resonate-and-Fire Neurons
• Techniques for Symbol Grounding with SATNet
• Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey
• Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution
• Improved Algorithms for Agnostic Pool-based Active Classification
• A high-bias, low-variance introduction to Machine Learning for physicists
• Towards In-Situ Failure Assessment: Deep Learning on DIC Results for Laminated Composites
• Confidence Calibration with Bounded Error Using Transformations
• CKConv: Continuous Kernel Convolution For Sequential Data
• Learning from N-Tuple Data with M Positive Instances: Unbiased Risk Estimation and Theoretical Guarantees
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion
• Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
• Provable Generalization Bounds for Deep Neural Networks with Momentum-Adaptive Gradient Dropout
• Swin Transformer V2: Scaling Up Capacity and Resolution
• Learning to compress and search visual data in large-scale systems
• A new deep learning-based approach for predicting the geothermal heat pump’s thermal power of a real bioclimatic house
• A general framework for interpretable neural learning based on local information-theoretic goal functions
• Consensus Modeling for Predicting Chemical Binding to Transthyretin as the Winning Solution of the Tox24 Challenge
• Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning
• Towards Query-Efficient Black-Box Adversary with Zeroth-Order Natural Gradient Descent
• Practical and Private (Deep) Learning without Sampling or Shuffling
• Influence Functions in Deep Learning Are Fragile
• End-to-end Phoneme Sequence Recognition using Convolutional Neural\n Networks
• A Multi-view Perspective of Self-supervised Learning
• FedBN: Federated Learning on Non-IID Features via Local Batch Normalization
• Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability
• A Renegotiable contract-theoretic incentive mechanism for Federated learning
• Domain Generalizable Continual Learning
• ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning
• WaMaIR: Image Restoration via Multiscale Wavelet Convolutions and Mamba-based Channel Modeling with Texture Enhancement
• Enabling Data Diversity: Efficient Automatic Augmentation via Regularized Adversarial Training
• A termination criterion for stochastic gradient descent for binary classification
• Video Swin Transformer
• On the Accuracy of CRNNs for Line-Based OCR: A Multi-Parameter Evaluation
• On the Neural Feature Ansatz for Deep Neural Networks
• Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling
• Unbiased Auxiliary Classifier GANs with MINE
• TVAE: Triplet-Based Variational Autoencoder using Metric Learning
• Low-Memory Implementations of Ridge Solutions for Broad Learning System with Incremental Learning
• Towards Reversible Model Merging For Low-rank Weights
• Learning Multi-Index Models with Hyper-Kernel Ridge Regression
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• On orthogonality and learning recurrent networks with long term dependencies
• APRIL: Auxiliary Physically-Redundant Information in Loss - A physics-informed framework for parameter estimation with a gravitational-wave case study
• Graph Neural Networks: A Review of Methods and Applications
• DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces
• Accelerating Federated Learning via Momentum Gradient Descent
• BI-MAML: Balanced Incremental Approach for Meta Learning
• Stable LLM Ensemble: Interaction between Example Representativeness and Diversity
• Information-Theoretic Criteria for Knowledge Distillation in Multimodal Learning
• Progressive multi-fidelity learning with neural networks for physical system predictions
• Randomness and Interpolation Improve Gradient Descent
• FigureQA: An Annotated Figure Dataset for Visual Reasoning
• Stochastic gradient descent methods for estimation with large data sets
• Detection of quantum information masking via machine learning
• Convolutional Attention in Betting Exchange Markets
• nnFormer: Interleaved Transformer for Volumetric Segmentation
• Long Expressive Memory for Sequence Modeling
• A Regularized Convolutional Neural Network for Semantic Image Segmentation
• F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (Extended Version)
• Tensor Logic: The Language of AI
• nuGPR: GPU-Accelerated Gaussian Process Regression with Iterative Algorithms and Low-Rank Approximations
• EMFlow: Data Imputation in Latent Space via EM and Deep Flow Models
• Neural Style Difference Transfer and Its Application to Font Generation
• Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines
• A deep learning theory for neural networks grounded in physics
• Emergence of Complex-Like Cells in a Temporal Product Network with Local Receptive Fields
• A Comprehensive Survey of Website Fingerprinting Attacks and Defenses in Tor: Advances and Open Challenges
• Optimised neural networks for online processing of ATLAS calorimeter data on FPGAs
• Identification of tea foliar diseases and pest damage under practical field conditions using a convolutional neural network
• Removing Spurious Features can Hurt Accuracy and Affect Groups Disproportionately
• Building machines that learn and think like people
• Quantifying Information Disclosure During Gradient Descent Using Gradient Uniqueness
• Building high-level features using large scale unsupervised learning
• MCE: Towards a General Framework for Handling Missing Modalities under Imbalanced Missing Rates
• f-INE: A Hypothesis Testing Framework for Estimating Influence under Training Randomness
• GenAttack: Practical Black-box Attacks with Gradient-Free Optimization
• Adversarial Weight Perturbation Helps Robust Generalization
• GO Gradient for Expectation-Based Objectives
• Reducing state updates via Gaussian-gated LSTMs
• Biological credit assignment through dynamic inversion of feedforward networks
• CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU
• Translution: Unifying Self-attention and Convolution for Adaptive and Relative Modeling
• Stochastic Training is Not Necessary for Generalization
• The Evolution of Artificial Intelligence Paradigms – Implications for Performance, Scalability, and Responsible Deployment
• A Novel lightweight Convolutional Neural Network, ExquisiteNetV2
• A Methodology for Transparent Logic-Based Classification Using a Multi-Task Convolutional Tsetlin Machine
• CloudSVM : Training an SVM Classifier in Cloud Computing Systems
• Differentially Private Dropout
• Computer-aided diagnosis of endobronchial ultrasound images using convolutional neural network
• TinyTorch: Building Machine Learning Systems from First Principles
• ChaRRNets: Channel Robust Representation Networks for RF Fingerprinting
• Techniques for Learning Binary Stochastic Feedforward Neural Networks
• A Cost Effective Solution for Road Crack Inspection using Cameras and Deep Neural Networks
• Scalable Model Compression by Entropy Penalized Reparameterization
• Parameter Transfer Unit for Deep Neural Networks
• Cross-View Policy Learning for Street Navigation
• OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation
• Wrapped Loss Function for Regularizing Nonconforming Residual\n Distributions
• cvpaper.challenge in 2015 - A review of CVPR2015 and DeepSurvey
• Phase-Aware Deep Learning with Complex-Valued CNNs for Audio Signal Applications
• Advancing Intoxication Detection: A Smartwatch-Based Approach
• A Generic Machine Learning Framework for Radio Frequency Fingerprinting
• Needles in Haystacks: On Classifying Tiny Objects in Large Images
• Drill the Cork of Information Bottleneck by Inputting the Most Important Data
• Uncertainty Estimates for Ordinal Embeddings
• A novel method for extracting interpretable knowledge from a spiking neural classifier with time-varying synaptic weights
• Multigrid Neural Memory
• Sales Forecast in E-commerce using Convolutional Neural Network
• Label Efficient Semi-Supervised Learning via Graph Filtering
• Deep Galaxy: Classification of Galaxies based on Deep Convolutional Neural Networks
• Polar Separable Transform for Efficient Orthogonal Rotation-Invariant Image Representation
• Unsupervised Image Captioning
• MNIST-NET10: A heterogeneous deep networks fusion based on the degree of certainty to reach 0.1 error rate. Ensembles overview and proposal
• Towards Neurocognitive-Inspired Intelligence: From AI's Structural Mimicry to Human-Like Functional Cognition
• SSGD: A safe and efficient method of gradient descent
• Quantum circuit optimization with deep reinforcement learning
• Exploring Data Aggregation and Transformations to Generalize across Visual Domains
• Do We Really Need Permutations? Impact of Width Expansion on Linear Mode Connectivity
• Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians
• Joint Architecture and Knowledge Distillation in CNN for Chinese Text Recognition
• TextHide: Tackling Data Privacy in Language Understanding Tasks
• Neural Network-based Automatic Factor Construction
• Conceptual capacity and effective complexity of neural networks
• Deep Generalized Convolutional Sum-Product Networks
• Weights initialization of neural networks for function approximation
• Neurocoder: Learning General-Purpose Computation Using Stored Neural Programs
• SGAS: Sequential Greedy Architecture Search
• Multi-Activation Hidden Units for Neural Networks with Random Weights
• Towards Causal Explanation Detection with Pyramid Salient-Aware Network
• Exploration in Action Space
• MMM: Quantum-Chemical Molecular Representation Learning for Combinatorial Drug Recommendation
• Disassembling Object Representations without Labels
• Bridging the Physics-Data Gap with FNO-Guided Conditional Flow Matching: Designing Inductive Bias through Hierarchical Physical Constraints
• Who Said Neural Networks Aren't Linear?
• A Rotation-Invariant Embedded Platform for (Neural) Cellular Automata
• Machine Learning for Radial Velocity Analysis I: Vision Transformers as a Robust Alternative for Detecting Planetary Candidates
• Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy
• Revealing the Temporally Stable Bimodal Energy Distribution of FRB 20121102A with a Tripled Burst Set from AI Detections
• Interactive reconstruction of Monte Carlo image sequences using a recurrent denoising autoencoder
• Enhancing Load Forecasting Accuracy in Smart Grids: A Novel Parallel Multichannel Network Approach Using 1D CNN and Bi‐LSTM Models
• Don't take it lightly: Phasing optical random projections with unknown operators
• Predicting Effective Diffusivity of Porous Media from Images by Deep Learning
• A survey on neural-symbolic learning systems
• Modeling COVID-19 Dynamics in German States Using Physics-Informed Neural Networks
• Chem-NMF: Multi-layer α-divergence Non-Negative Matrix Factorization for Cardiorespiratory Disease Clustering, with Improved Convergence Inspired by Chemical Catalysts and Rigorous Asymptotic Analysis
• Associative Memory Model with Neural Networks: Memorizing multiple images with one neuron
• Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving
• Angular Constraint Embedding via SpherePair Loss for Constrained Clustering
• Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
• TreeNet: Layered Decision Ensembles
• Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifiers
• Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
• QDeepGR4J: Quantile-based ensemble of deep learning and GR4J hybrid rainfall-runoff models for extreme flow prediction with uncertainty quantification
• A Tropical Approach to Neural Networks with Piecewise Linear Activations
• Learning the detector in optical tomography
• Evaluation of fish feeding intensity in aquaculture using a convolutional neural network and machine vision
• A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
• "Tom" pet robot applied to urban autism
• Egalitarian Gradient Descent: A Simple Approach to Accelerated Grokking
• Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
• WebVision Database: Visual Learning and Understanding from Web Data
• Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing
• FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
• Scaling Limits of Wide Neural Networks with Weight Sharing: Gaussian Process Behavior, Gradient Independence, and Neural Tangent Kernel Derivation
• Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
• Unlearning in Diffusion models under Data Constraints: A Variational Inference Approach
• Reward Augmented Maximum Likelihood for Neural Structured Prediction
• An Efficient Approach to Informative Feature Extraction from Multimodal Data
• A gradual, semi-discrete approach to generative network training via\n explicit Wasserstein minimization
• FHEON: A Configurable Framework for Developing Privacy-Preserving Neural Networks Using Homomorphic Encryption
• No bad local minima: Data independent training error guarantees for\n multilayer neural networks
• ConvBERT: Improving BERT with Span-based Dynamic Convolution
• A Reinforcement Learning Based Encoder-Decoder Framework for Learning Stock Trading Rules
• Evaluation of Transfer Learning for Classification of: (1) Diabetic\n Retinopathy by Digital Fundus Photography and (2) Diabetic Macular Edema,\n Choroidal Neovascularization and Drusen by Optical Coherence Tomography
• Exploring the Hierarchical Reasoning Model for Small Natural-Image Classification Without Augmentation
• MECKD: Deep Learning-Based Fall Detection in Multilayer Mobile Edge Computing With Knowledge Distillation
• Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
• COMET: Co-Optimization of a CNN Model using Efficient-Hardware OBC Techniques
• Focal-plane wavefront sensing with moderately broadband light using a short multi-mode fiber
• Modeling Quantum Geometry for Fractional Chern Insulators with unsupervised learning
• Dale meets Langevin: A Multiplicative Denoising Diffusion Model
• Using Fourier Analysis and Mutant Clustering to Accelerate DNN Mutation Testing
• Provenance Networks: End-to-End Exemplar-Based Explainability
• Quantum-inspired Benchmark for Estimating Intrinsic Dimension
• Unsupervised Change Detection in Multi-temporal VHR Images Based on Deep Kernel PCA Convolutional Mapping Network
• Multiparametric Deep Learning Tissue Signatures for Muscular Dystrophy:\n Preliminary Results
• Indices Matter: Learning to Index for Deep Image Matting
• Neural network-based clustering using pairwise constraints
• Generalizing to Unseen Domains via Adversarial Data Augmentation
• Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
• Collaborative Machine Learning Markets with Data-Replication-Robust Payments
• Personalized Federated Learning with First Order Model Optimization
• SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
• Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
• Generative AI for subgrid turbulence in large-eddy simulations
• Continual Learning with Query-Only Attention
• Randomness In Neural Network Training: Characterizing The Impact of Tooling
• Fast frequency reconstruction using Deep Learning for event recognition in ring laser data
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• On zero-shot recognition of generic objects
• Deep Neural Networks are Easily Fooled: High Confidence Predictions for\n Unrecognizable Images
• Beyond the Memory Wall: A Case for Memory-centric HPC System for Deep\n Learning
• TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL
• Stealing AI Model Weights Through Covert Communication Channels
• Uncertainty Quantification for Regression using Proper Scoring Rules
• Data-to-Energy Stochastic Dynamics
• FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
• Marginal Flow: a flexible and efficient framework for density estimation
• Reevaluating Convolutional Neural Networks for Spectral Analysis: A Focus on Raman Spectroscopy
• From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks
• Graph Distribution-valued Signals: A Wasserstein Space Perspective
• Using Images from a Video Game to Improve the Detection of Truck Axles
• Ascent Fails to Forget
• DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis
• Cold-Start Active Correlation Clustering
• Accelerating Dynamic Image Graph Construction on FPGA for Vision GNNs
• ClustRecNet: A Novel End-to-End Deep Learning Framework for Clustering Algorithm Recommendation
• Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
• Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
• FS-KAN: Permutation Equivariant Kolmogorov-Arnold Networks via Function Sharing
• PEARL: Performance-Enhanced Aggregated Representation Learning
• Advancing Automated Fish Size Estimation From Images: Applications, Challenges and a Case Study for Images Without a Specified Reference Object
• Materials, processes, devices and applications of magnetoresistive random access memory
• What Are We Automating? On the Need for Vision and Expertise When Deploying AI Systems
• Regularized Autoencoders via Relaxed Injective Probability Flow
• VN-EGNN: E(3)- and SE(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification
• Climate impacts and future trends of hailstorms in China based on millennial records
• Semi-supervised deep learning by metric embedding
• Learning to Diversify for Single Domain Generalization
• Deep Learning with Limited Numerical Precision
• Deep Auto-encoder with Neural Response
• Progressive Domain Expansion Network for Single Domain Generalization
• Incorporating Deep Features in the Analysis of Tissue Microarray Images
• Learning to generate filters for convolutional neural networks
• Nonparametric Learning of Two-Layer ReLU Residual Units
• Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformers
• A Biophysical-Model-Informed Source Separation Framework For EMG Decomposition
• AI Safety, Alignment, and Ethics (AI SAE)
• Tent: Fully Test-time Adaptation by Entropy Minimization
• Differentiable Sparsity via D-Gating: Simple and Versatile Structured Penalization
• Preserving Cross-Modal Stability for Visual Unlearning in Multimodal Scenarios
• Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
• Similarity-Based Assessment of Computational Reproducibility in Jupyter Notebooks
• Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery
• Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
• Disentanglement of Variations with Multimodal Generative Modeling
• CNN-based Segmentation of Medical Imaging Data
• Black-Box Adversarial Attack with Transferable Model-based Embedding
• Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
• Seeing the Unseen in Low-light Spike Streams
• The unbearable slowness of being: Why do we live at 10 bits/s?
• Temporal image sandwiches enable link between functional data analysis and deep learning for single-plant cotton senescence
• Soft Sampling for Robust Object Detection
• Sparse, Collaborative, or Nonnegative Representation: Which Helps Pattern Classification?
• Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection
• Deep Adversarial Belief Networks
• DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligence
• Adaptive Sampling for Stochastic Risk-Averse Learning
• An optimized system to solve text-based CAPTCHA
• Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
• How Secure is Distributed Convolutional Neural Network on IoT Edge Devices?
• AntiFLipper: A Secure and Efficient Defense Against Label-Flipping Attacks in Federated Learning
• PAPER: Privacy-Preserving Convolutional Neural Networks using Low-Degree Polynomial Approximations and Structural Optimizations on Leveled FHE
• Detection of Hidden Low-Frequency Earthquakes in Southern Vancouver Island with Deep Learning
• Interpreting Deep Learning: The Machine Learning Rorschach Test?
• Exploiting long-term temporal dynamics for video captioning
• Taming the ReLU with Parallel Dither in a Deep Neural Network
• "Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training Deep Neural Networks
• RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks
• Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based Approach
• Learning from Synthetic Data Using a Stacked Multichannel Autoencoder
• Word, graph and manifold embedding from Markov processes
• CLAMShell: Speeding up Crowds for Low-latency Data Labeling
• A Dataset of Naturally Occurring, Whole-Body Background Activity to Reduce Gesture Conflicts
• Implicit Generative Modeling of Random Noise during Training for\n Adversarial Robustness
• Mining Domain Knowledge: Improved Framework towards Automatically Standardizing Anatomical Structure Nomenclature in Radiotherapy
• Power and Accuracy of Multi-Layer Perceptrons (MLPs) under\n Reduced-voltage FPGA BRAMs Operation
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual\n Recognition
• Design of Reconfigurable Multi-Operand Adder for Massively Parallel\n Processing
• Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments
• Efficiency Boost in Decentralized Optimization: Reimagining Neighborhood Aggregation with Minimal Overhead
• Slicing Wasserstein Over Wasserstein Via Functional Optimal Transport
• Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
• Regularized Overestimated Newton
• Learning to Look: Cognitive Attention Alignment with Vision-Language Models
• LV-BERT: Exploiting Layer Variety for BERT
• Classification Uncertainty of Deep Neural Networks Based on Gradient\n Information
• Reliable counting of weakly labeled concepts by a single spiking neuron model
• Building Safer AGI by introducing Artificial Stupidity
• Laplacian Smoothing Gradient Descent
• Deep Watershed Detector for Music Object Recognition
• Sliced Recurrent Neural Networks
• A Fast Globally Linearly Convergent Algorithm for the Computation of\n Wasserstein Barycenters
• Active Testing: Sample-Efficient Model Evaluation
• Accelerating Deep Neural Networks with Spatial Bottleneck Modules
• Clustering and Learning from Imbalanced Data
• Deep-RBF Networks Revisited: Robust Classification with Rejection
• Improving neural networks by preventing co-adaptation of feature detectors
• Null-Space Filtering for Data-Free Continual Model Merging: Preserving Transparency, Promoting Fidelity
• LAVA: Explainability for Unsupervised Latent Embeddings
• Shaping Initial State Prevents Modality Competition in Multi-modal Fusion: A Two-stage Scheduling Framework via Fast Partial Information Decomposition
• Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
• Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning
• Staying on the Manifold: Geometry-Aware Noise Injection
• Characterizing the Performance of Accelerated Jetson Edge Devices for Training Deep Learning Models
• Efficient Parameter-free Clustering Using First Neighbor Relations
• Rich feature hierarchies for accurate object detection and semantic\n segmentation
• Unsupervised Domain Adaptation by Backpropagation
• Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update
• Does the Adam Optimizer Exacerbate Catastrophic Forgetting?
• Widening the Pipeline in Human-Guided Reinforcement Learning with Explanation and Context-Aware Data Augmentation
• Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics
• Open-source Stand-Alone Versatile Tensor Accelerator
• Efficiently Attacking Memorization Scores
• ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research
• Annealed Generative Adversarial Networks
• Learning to see across Domains and Modalities
• Detecting Positive Selection by Modeling Structure Within Images of Genetic Variation
• <scp> S ² </scp> ‐ <scp>PepAnalyst</scp> : A Web Tool for Predicting Plant Small Signalling Peptides
• Machine Learning in Next-Generation Polymer Composites: Recent Advances and Perspectives
• Trainability and Mode Separation of Mixed IQP-QCBMs
• Stochastic gradient descent with random learning rate
• Multi-task Learning by Leveraging the Semantic Information
• On the distance between two neural networks and the stability of learning
• Training Feedforward Neural Networks with Standard Logistic Activations\n is Feasible
• Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization
• Lets keep it simple, Using simple architectures to outperform deeper and\n more complex architectures
• Deep learning of fossil pollen morphology reveals 25,000 years of ecological change in East African grasslands
• Analog-electronic implementation of a harmonic oscillator recurrent neural network
• Shortcut to Nowhere: Demystifying Deep Spurious Regression
• Fast approximate loss change for active learning on imbalanced data
• Feature refinement: An expression-specific feature learning and fusion method for micro-expression recognition
• When AI Meets Science: Research Diversity, Interdisciplinarity, Visibility, and Retractions across Disciplines in a Global Surge
• Improving the Performance and Learning Stability of Parallelizable RNNs Designed for Ultra-Low Power Applications
• A Framework for Deep Constrained Clustering
• Bias-Aware Heapified Policy for Active Learning
• Heating up decision boundaries: isocapacitory saturation, adversarial scenarios and generalization bounds
• Estimating uncertainty in flood model outputs using machine learning informed by Monte Carlo analysis
• On herbarium specimen images and artificial intelligence
• Selecting Data Augmentation for Simulating Interventions
• Learning Sparse High Dimensional Filters: Image Filtering, Dense CRFs\n and Bilateral Neural Networks
• Switched linear projections for neural network interpretability
• Fuzzy Semantic Segmentation of Breast Ultrasound Image with Breast Anatomy Constraints
• VINNAS: Variational Inference-based Neural Network Architecture Search
• Literature review on vulnerability detection using NLP technology
• Learning to Continually Learn Rapidly from Few and Noisy Data
• Linear Response Methods for Accurate Covariance Estimates from Mean\n Field Variational Bayes
• A Deep Learning Framework for Classification of in vitro Multi-Electrode Array Recordings
• Unbounded Output Networks for Classification
• Zero-shifting Technique for Deep Neural Network Training on Resistive Cross-point Arrays
• Multi-layered Spiking Neural Network with Target Timestamp Threshold Adaptation and STDP
• Ensemble of convolution neural networks on heterogeneous signals for sleep stage scoring
• TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
• Data Noising as Smoothing in Neural Network Language Models
• A Framework for Deep Constrained Clustering -- Algorithms and Advances
• Traversing the Continuous Spectrum of Image Retrieval with Deep Dynamic Models
• A contrastive rule for meta-learning
• Using artificial intelligence to document the hidden RNA virosphere
• Transporting Task Vectors across Different Architectures without Training
• Ristretto: Hardware-Oriented Approximation of Convolutional Neural\n Networks
• Dense Adaptive Cascade Forest: A Self Adaptive Deep Ensemble for Classification Problems
• Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild
• Towards adversarial robustness with 01 loss neural networks
• Structural network measures reveal the emergence of heavy-tailed degree distributions in lottery ticket multilayer perceptrons
• Neuromorphic Computing via Fission‐based Broadband Frequency Generation
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems
• Deep Bayesian Unsupervised Lifelong Learning
• Wireless for Machine Learning
• Auto-Encoding Twin-Bottleneck Hashing
• A Geometric Approach to Online Streaming Feature Selection
• Uniform Priors for Data-Efficient Transfer
• Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning
• Convolutional Channel Features
• Convolutional neural networks outperform other presence-only species distribution modeling algorithms
• Practical Lossless Compression with Latent Variables using Bits Back Coding
• Practical Quasi-Newton Methods for Training Deep Neural Networks
• Scaling Up Exact Neural Network Compression by ReLU Stability
• AutoFlow: Learning a Better Training Set for Optical Flow
• Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
• Learning Purified Feature Representations from Task-irrelevant Labels
• Merchant Category Identification Using Credit Card Transactions
• Constraining Logits by Bounded Function for Adversarial Robustness
• Memory-Efficient CNN Accelerator Based on Interlayer Feature Map Compression
• VAEs in the Presence of Missing Data
• Learning a visuomotor controller for real world robotic grasping using simulated depth images
• BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning
• Can We Faithfully Represent Masked States to Compute Shapley Values on a DNN?
• Block-Matching Convolutional Neural Network for Image Denoising
• An Features Extraction and Recognition Method for Underwater Acoustic Target Based on ATCNN
• Neural Image Compression and Explanation
• Adversarial Phenomenon in the Eyes of Bayesian Deep Learning
• Relating Input Concepts to Convolutional Neural Network Decisions
• Biologically-inspired Salience Affected Artificial Neural Network (SANN)
• Classification and Retrieval of Digital Pathology Scans: A New Dataset
• Adversarial Robustness Across Representation Spaces
• Double cycle-consistent generative adversarial network for unsupervised conditional generation
• Learning to Separate Clusters of Adversarial Representations for Robust Adversarial Detection
• Graphs for deep learning representations
• LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
• How Much Can I Trust You? -- Quantifying Uncertainties in Explaining Neural Networks
• Neural Conditional Gradients
• Convergence of backpropagation with momentum for network architectures with skip connections
• Deep Image Feature Learning with Fuzzy Rules
• Characterization of Excess Risk for Locally Strongly Convex Population Risk
• Visual Recognition Using Directional Distribution Distance
• Adversarial Examples in Constrained Domains
• ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction
• Improving Outdoor Multi-cell Fingerprinting-based Positioning via Mobile Data Augmentation
• Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark
• Freehand Sketch Recognition Using Deep Features
• Beyond Word-based Language Model in Statistical Machine Translation
• Scalable Compression of Deep Neural Networks
• A Tutorial on Quantum Convolutional Neural Networks (QCNN)
• Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics
• FedOC: Multi-Server FL with Overlapping Client Relays in Wireless Edge Networks
• Learning to Be Cautious
• Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data
• Robustness Feature Adapter for Efficient Adversarial Training
• A Fast Learning Algorithm for Deep Belief Nets
• Uncovering Privacy Vulnerabilities through Analytical Gradient Inversion Attacks
• Deep Recurrent Q-Learning for Partially Observable MDPs
• Variable selection with false discovery rate control in deep neural networks
• Conformal Prediction based Spectral Clustering
• PointNet: Deep Learning on Point Sets for 3D Classification and\n Segmentation
• EdgeCNN: Convolutional Neural Network Classification Model with small inputs for Edge Computing
• Tensor-based Cooperative Control for Large Scale Multi-intersection Traffic Signal Using Deep Reinforcement Learning and Imitation Learning
• Effective and efficient ROI-wise visual encoding using an end-to-end CNN regression model and selective optimization
• Neural Kernels Without Tangents
• Context-Aware Multipath Networks
• Robustifying Models Against Adversarial Attacks by Langevin Dynamics
• Bilateral Distribution Compression: Reducing Both Data Size and Dimensionality
• Clustering and Unsupervised Anomaly Detection with L2 Normalized Deep\n Auto-Encoder Representations
• Effectiveness of Data Augmentation in Cellular-based Localization Using Deep Learning
• Optimizing Split Federated Learning with Unstable Client Participation
• Compact representation of transonic airfoil buffet flows with observable-augmented machine learning
• All-optical machine learning using diffractive deep neural networks
• Faster On-Device Training Using New Federated Momentum Algorithm
• Deep learning and the Schrödinger equation
• Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher
• FPGA-Based Accelerators of Deep Learning Networks for Learning and Classification: A Review
• Automatic Intermodal Loading Unit Identification using Computer Vision: A Scoping Review
• Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning
• Tangent Space Separability in Feedforward Neural Networks
• Discriminative convolutional Fisher vector network for action recognition
• Fooling Vision and Language Models Despite Localization and Attention Mechanism
• MARS: A Malignity-Aware Backdoor Defense in Federated Learning
• From handcrafted to deep local features
• Deep Clustering for Unsupervised Learning of Visual Features
• Quantifying the effect of representations on task complexity
• TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing
• DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation
• Building effective deep neural network architectures one feature at a time
• Distributional Generalization: A New Kind of Generalization
• 3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues
• Graph Coloring for Multi-Task Learning
• Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
• A Deep-Learning-Driven Optimization-Based Inverse Solver for Accelerating the Marchenko Method
• Federated Learning with Differential Privacy: Algorithms and Performance Analysis
• A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
• Delving into Cryptanalytic Extraction of PReLU Neural Networks
• Spatio-temporal, multi-field deep learning of shock propagation in meso-structured media
• EMNIST: an extension of MNIST to handwritten letters
• Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects
• A Survey and Comparative Evaluation of Intrinsic Dimension Estimators under the Manifold Hypothesis
• Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification
• Robustness through Data Augmentation Loss Consistency
• On Deep Multi-View Representation Learning: Objectives and Optimization
• A CNN-LSTM-Based Model to Forecast Stock Prices
• MoE-CE: Enhancing Generalization for Deep Learning based Channel Estimation via a Mixture-of-Experts Framework
• Region-Aware Deformable Convolutions
• Emulating Human-like Adaptive Vision for Efficient and Flexible Machine Visual Perception
• Effect of Initial Configuration of Weights on Training and Function of Artificial Neural Networks
• CoDoL: Conditional Domain Prompt Learning for Out-of-Distribution Generalization
• Leveraging Geometric Visual Illusions as Perceptual Inductive Biases for Vision Models
• Trust but Verify: An Information-Theoretic Explanation for the Adversarial Fragility of Machine Learning Systems, and a General Defense against Adversarial Attacks
• Exact Stochastic Second Order Deep Learning
• FAWN: A MultiEncoder Fusion-Attention Wave Network for Integrated Sensing and Communication Indoor Scene Inference
• Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
• Crafting GBD-Net for Object Detection
• One-step Multi-view Clustering With Adaptive Low-rank Anchor-graph Learning
• Emotion-Aware Speech Generation with Character-Specific Voices for Comics
• Chameleon: Integrated Sensing and Communication with Sub-Symbol Beam Switching in mmWave Networks
• Stochastic Backward Euler: An Implicit Gradient Descent Algorithm for k-means Clustering
• Towards Interrogating Discriminative Machine Learning Models
• Energy Attack: On Transferring Adversarial Examples
• Survey on semantic segmentation using deep learning techniques
• Recent advances on federated learning: A systematic survey
• Deep Learning For Computer Vision Tasks: A review
• Open-World Class Discovery with Kernel Networks
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
• Learning FRAME Models Using CNN Filters
• Asynchronous Multi-Task Learning
• DF-LLaVA: Unlocking MLLMs for Synthetic Image Detection via Knowledge Injection and Conflict-Driven Self-Reflection
• Deep Predictive Coding Network for Object Recognition
• Modeling Information Flow Through Deep Neural Networks
• Probabilistic Neural Network with Complex Exponential Activation\n Functions in Image Recognition using Deep Learning Framework
• Triple Generative Adversarial Nets
• clcNet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions
• Progressive Identification of True Labels for Partial-Label Learning
• Data Leakage in Visual Datasets
• Online Learning to Sample
• FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning
• Difficulty-aware Image Super Resolution via Deep Adaptive Dual-Network
• On Tilted Losses in Machine Learning: Theory and Applications
• Deep Multi-task Learning for Railway Track Inspection
• Unsupervised Representation Learning by Predicting Image Rotations
• Reprogrammable Electro-Optic Nonlinear Activation Functions for Optical Neural Networks
• Vision-Language Models for Vision Tasks: A Survey
• Large Language Models and the Reverse Turing Test
• Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks
• On the Out-of-Distribution Backdoor Attack for Federated Learning
• Shapes Characterization on Address Event Representation Using Histograms of Oriented Events and an Extended LBP Approach
• ConceptFlow: Hierarchical and Fine-grained Concept-Based Explanation for Convolutional Neural Networks
• B-TGAT: A Bi-directional Temporal Graph Attention Transformer for Clustering Multivariate Spatiotemporal Data
• On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions
• ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
• Modelling and analysis of the 8 filters from the "master key filters hypothesis" for depthwise-separable deep networks in relation to idealized receptive fields based on scale-space theory
• Permutohedral Lattice CNNs
• On the Adversarial Robustness of Neural Networks without Weight\n Transport
• Multi-level Wavelet Convolutional Neural Networks
• Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers
• A Robust and Precise ConvNet for small non-coding RNA classification\n (RPC-snRC)
• Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion
• Multipartite Pooling for Deep Convolutional Neural Networks
• Learning in an Uncertain World: Representing Ambiguity Through Multiple\n Hypotheses
• A Survey on Neural Architecture Search
• On the Decision Boundary of Deep Neural Networks
• Reinforcement Learning for Learning Rate Control
• A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model
• Scalable Kernel Methods via Doubly Stochastic Gradients
• Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach
• Proposal Learning for Semi-Supervised Object Detection
• The Search for Sparse, Robust Neural Networks
• Overlearning Reveals Sensitive Attributes
• Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance
• Unobtrusive Pain Monitoring in Older Adults with Dementia using Pairwise\n and Contrastive Training
• Scene Labeling with Contextual Hierarchical Models
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
• Averaged-DQN: Variance Reduction and Stabilization for Deep\n Reinforcement Learning
• The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition
• Robust Conditional GAN from Uncertainty-Aware Pairwise Comparisons
• Energy-Efficient Quantized Federated Learning for Resource-constrained IoT devices
• Curvature as a tool for evaluating dimensionality reduction and estimating intrinsic dimension
• Towards Model-Agnostic Adversarial Defenses using Adversarially Trained Autoencoders
• Unsupervised Domain Adaptation of Black-Box Source Models
• SEALion: a Framework for Neural Network Inference on Encrypted Data
• Reconstruction of Natural Visual Scenes from Neural Spikes with Deep Neural Networks
• Learning Deep ResNet Blocks Sequentially using Boosting Theory
• Rademacher Complexity for Adversarially Robust Generalization
• SPMFormer: Simplified Physical Model-based transformer with cross-space loss for underwater image enhancement
• R-Transformer: Recurrent Neural Network Enhanced Transformer
• Adaptive Machine Unlearning
• Diagnosing and Enhancing VAE Models
• Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies
• MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
• Why Attentions May Not Be Interpretable?
• Rate-Distortion Optimization Guided Autoencoder for Isometric Embedding in Euclidean Latent Space
• Neural Predictive Belief Representations
• Meta-Learning Mean Functions for Gaussian Processes
• Learning from Uncertain Similarity and Unlabeled Data
• Artificial Neural Networks for Neuroscientists: A Primer
• On the role of Model Uncertainties in Bayesian Optimization
• Take it in your stride: Do we need striding in CNNs?
• Convolutional Neural Networks for Accurate Measurement of Train Speed
• Twitter Sentiment on Affordable Care Act using Score Embedding
• Evaluating State-of-the-Art Classification Models Against Bayes Optimality
• EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness against Adversarial Attacks
• Adaptive Spatial Goodness Encoding: Advancing and Scaling Forward-Forward Learning Without Backpropagation
• Mitigate Parasitic Resistance in Resistive Crossbar-based Convolutional Neural Networks
• Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers
• Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning
• Learning Disentangled Representations with Reference-Based Variational Autoencoders
• DA-RefineNet:A Dual Input Whole Slide Image Segmentation Algorithm Based on Attention
• Generalizing Tree Probability Estimation via Bayesian Networks
• Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networks
• Stochastic Neural Network with Kronecker Flow
• Supervised Deep Sparse Coding Networks
• Compact Device Models for FinFET and Beyond
• Generating 3D Adversarial Point Clouds
• Stabilizing Data-Free Model Extraction
• Robustifying Diffusion-Denoised Smoothing Against Covariate Shift
• Learning Face Representation from Scratch
• A COLD Approach to Generating Optimal Samples
• Learnable Gabor modulated complex-valued networks for orientation robustness
• Deep Learning for Generic Object Detection: A Survey
• Two ways to knowledge?
• Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise
• Multiple Instance Learning Convolutional Neural Networks for Object Recognition
• Survey: Machine Learning in Production Rendering
• A Capsule-unified Framework of Deep Neural Networks for Graphical Programming
• FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projection
• Quantifying and testing dependence to categorical variables
• CatBoost for big data: an interdisciplinary review
• Learning Implicit Generative Models Using Differentiable Graph Tests
• FALCON: Feature Driven Selective Classification for Energy-Efficient\n Image Recognition
• Packing Sparse Convolutional Neural Networks for Efficient Systolic Array Implementations: Column Combining Under Joint Optimization
• Micro-Attention for Micro-Expression recognition
• Contrastive Learning with Stronger Augmentations
• Importance Sampling via Local Sensitivity
• The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks
• Parameterized Knowledge Transfer for Personalized Federated Learning
• Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter
• Momentum-Based Variance Reduction in Non-Convex SGD
• Momentum-based variance-reduced proximal stochastic gradient method for composite nonconvex stochastic optimization
• Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks
• Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers
• Simple, Scalable, and Stable Variational Deep Clustering
• Machine Learning Confirms GW231123 is a "Lite" Intermediate Mass Black Hole Merger
• Sequential Spectral Clustering of Data Sequences
• Anomaly Recognition from surveillance videos using 3D Convolutional Neural Networks
• Geom-SPIDER-EM: Faster Variance Reduced Stochastic Expectation Maximization for Nonconvex Finite-Sum Optimization
• Images in Motion?: A First Look into Video Leakage in Collaborative Deep Learning
• CoSwin: Convolution Enhanced Hierarchical Shifted Window Attention For Small-Scale Vision
• Dynamics of Deep Neural Networks and Neural Tangent Hierarchy
• Learning Implicit Generative Models by Teaching Explicit Ones
• Generating Semantic Adversarial Examples via Feature Manipulation
• Deep learning for extracting protein-protein interactions from biomedical literature
• Decentralized Stochastic Nonconvex Optimization under the (L₀,L₁)-Smoothness
• Energy-convergence trade off for the training of neural networks on bio-inspired hardware
• Multispectral CT Denoising via Simulation-Trained Deep Learning: Experimental Results at the ESRF BM18
• Learning From Noisy Labels By Regularized Estimation Of Annotator Confusion
• Phishing Webpage Detection: Unveiling the Threat Landscape and Investigating Detection Techniques
• Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks
• On the Complexity of Labeled Datasets
• PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments
• Label Smoothing++: Enhanced Label Regularization for Training Neural Networks
• Sparsity in Deep Neural Networks - An Empirical Investigation with\n TensorQuant
• Scalable Coupling of Deep Learning with Logical Reasoning
• Experiments with Rich Regime Training for Deep Learning
• OCTANE -- Optimal Control for Tensor-based Autoencoder Network Emergence: Explicit Case
• Hammer and Anvil: A Principled Defense Against Backdoors in Federated Learning
• Learning Augmentation Distributions using Transformed Risk Minimization
• Multimodal Contrastive Pretraining of CBCT and IOS for Enhanced Tooth Segmentation
• REPAIR: Removing Representation Bias by Dataset Resampling
• Making AI Forget You: Data Deletion in Machine Learning
• User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization
• Dataset Distillation
• MEGG: Replay via Maximally Extreme GGscore in Incremental Learning for Neural Recommendation Models
• Using Optimal Transport Aligned Latent Embeddings for Separated Flow Analysis
• Spectral and Rhythm Feature Performance Evaluation for Category and Class Level Audio Classification with Deep Convolutional Neural Networks
• Convolution Neural Network Hyperparameter Optimization Using Simplified Swarm Optimization
• Can deep learning beat numerical weather prediction?
• SteganoGAN: High Capacity Image Steganography with GANs
• Neural Anisotropy Directions
• Adding noise to the input of a model trained with a regularized objective
• Fake News Detection on Social Media using Geometric Deep Learning
• Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysis
• Evaluating the Impact of Adversarial Attacks on Traffic Sign Classification using the LISA Dataset
• Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification
• Learning Long-Term Dependencies in Irregularly-Sampled Time Series
• On the Evaluation of Conditional GANs
• RotoGrad: Gradient Homogenization in Multitask Learning
• On the Convergence of FedAvg on Non-IID Data
• Machine Learning: Algorithms, Real-World Applications and Research Directions
• Geometry of Optimization and Implicit Regularization in Deep Learning
• Experience Report: Deep Learning-based System Log Analysis for Anomaly Detection
• Image Enhanced Rotation Prediction for Self-Supervised Learning
• Full Integer Arithmetic Online Training for Spiking Neural Networks
• Lookup multivariate Kolmogorov-Arnold Networks
• PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
• High-Quality Tomographic Image Reconstruction Integrating Neural Networks and Mathematical Optimization
• Albumentations: Fast and Flexible Image Augmentations
• Less-forgetful Learning for Domain Expansion in Deep Neural Networks
• ConstStyle: Robust Domain Generalization with Unified Style Transformation
• Agglomerative Attention
• RepVGG: Making VGG-style ConvNets Great Again
• A brain-inspired paradigm for scalable quantum vision
• Closer to Reality: Practical Semi-Supervised Federated Learning for Foundation Model Adaptation
• Variational Federated Multi-Task Learning
• Pseudo-positive regularization for deep person re-identification
• TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
• Hyperbolic Large Language Models
• TWINs: Two Weighted Inconsistency-reduced Networks for Partial Domain Adaptation
• Channel Pruning for Accelerating Very Deep Neural Networks
• Viewmaker Networks: Learning Views for Unsupervised Representation Learning
• Universality of physical neural networks with multivariate nonlinearity
• Dimensionality-Driven Learning with Noisy Labels
• Dynamic Attention-based Communication-Efficient Federated Learning
• On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
• NSML: Meet the MLaaS platform with a real-world case study
• Variational Autoencoder with Learned Latent Structure
• The Weighted Tsetlin Machine: Compressed Representations with Weighted\n Clauses
• Unsupervised Regenerative Learning of Hierarchical Features in Spiking\n Deep Networks for Object Recognition
• Pixel-wise Conditioned Generative Adversarial Networks for Image\n Synthesis and Completion
• Pipe-SGD: A Decentralized Pipelined SGD Framework for Distributed Deep Net Training
• The Advantage of Fine-Grained Training
• A Study of Gradient Variance in Deep Learning
• A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection
• Flattening Sharpness for Dynamic Gradient Projection Memory Benefits\n Continual Learning
• Painting the market: generative diffusion models for financial limit order book simulation and forecasting
• Discovering Software Parallelization Points Using Deep Neural Networks
• On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
• Towards Open World Detection: A Survey
• Plug-and-Play Latent Diffusion for Electromagnetic Inverse Scattering with Application to Brain Imaging
• VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation
• Surformer v2: A Multimodal Classifier for Surface Understanding from Touch and Vision
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• Suppressing the Unusual: towards Robust CNNs using Symmetric Activation Functions
• Man versus Machine: AutoML and Human Experts' Role in Phishing Detection
• Stylized Neural Painting
• Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation
• Selective Structural Ablation for Efficient 3D Point Cloud Signal Processing
• Compressing Neural Networks using the Variational Information Bottleneck
• Deep Complex Networks for Protocol-Agnostic Radio Frequency Device Fingerprinting in the Wild
• Improving the Accuracy and Hardware Efficiency of Neural Networks Using Approximate Multipliers
• Grader Variability and the Importance of Reference Standards for Evaluating Machine Learning Models for Diabetic Retinopathy
• Detecting Regional Spurious Correlations in Vision Transformers via Token Discarding
• Deeply learned face representations are sparse, selective, and robust
• AM-ConvGRU: a spatio-temporal model for typhoon path prediction
• Open Set Domain Adaptation by Backpropagation
• Diffusion Generative Models Meet Compressed Sensing, with Applications to Imaging and Finance
• Generalizing Variational Autoencoders with Hierarchical Empirical Bayes
• 1D convolutional neural networks and applications: A survey
• Reconstruction Student with Attention for Student-Teacher Pyramid Matching
• Spatiotemporal Pyramid Network for Video Action Recognition
• Effective writing style imitation via combinatorial paraphrasing
• Defective Convolutional Networks
• Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces
• Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review
• Enhancing Gradient Variance and Differential Privacy in Quantum Federated Learning
• Moment Matching for Multi-Source Domain Adaptation
• Tensor Network for Supervised Learning at Finite Temperature
• Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows
• Estudio de la eficiencia en la escalabilidad de GPUs para el entrenamiento de Inteligencia Artificial
• Sparse Autoencoder Neural Operators: Model Recovery in Function Spaces
• Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks
• The Optimiser Hidden in Plain Sight: Training with the Loss Landscape's Induced Metric
• LSAM: Asynchronous Distributed Training with Landscape-Smoothed Sharpness-Aware Minimization
• Isolated Bangla Handwritten Character Classification using Transfer Learning
• TRADI: Tracking deep neural network weight distributions for uncertainty\n estimation
• AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
• End-to-end acoustic modeling using convolutional neural networks for HMM-based automatic speech recognition
• A Differential Manifold Perspective and Universality Analysis of Continuous Attractors in Artificial Neural Networks
• Gradient Estimation Methods of Approximate Multipliers for High-Accuracy Retraining of Deep Learning Models
• LINKER: Learning Interactions Between Functional Groups and Residues With Chemical Knowledge-Enhanced Reasoning and Explainability
• Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
• Network Implosion: Effective Model Compression for ResNets via Static Layer Pruning and Retraining
• Selfless Sequential Learning
• RotaTouille: Rotation Equivariant Deep Learning for Contours
• A Convolutional Hierarchical Deep-learning Neural Network (C-HiDeNN) Framework for Non-linear Finite Element Analysis
• Vision encoders should be image size agnostic and task driven
• Lightweight Combinational Machine Learning Algorithm for Sorting Canine Torso Radiographs
• Hierarchical Single-Linkage Clustering for Community Detection with Overlaps and Outliers
• Pedestrian Attribute Recognition: A Survey
• Kernel-based Generative Learning in Distortion Feature Space
• Edge-Native Digitization of Handwritten Marksheets: A Hybrid Heuristic-Deep Learning Framework
• Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection
• Lifelong Learning with Dynamically Expandable Networks
• Multi-View Spatial-Temporal Graph Convolutional Networks with Domain Generalization for Sleep Stage Classification
• Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
• An Investigation of Visual Foundation Models Robustness
• Ridesourcing Car Detection by Transfer Learning
• Frame Averaging for Invariant and Equivariant Network Design
• Enhancing Fitness Movement Recognition with Attention Mechanism and Pre-Trained Feature Extractors
• Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity
• Learning Optimal Linear Regularizers
• Bayes Optimal Early Stopping Policies for Black-Box Optimization
• Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
• AReLU: Attention-based Rectified Linear Unit
• Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
• Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
• Motor Imagery EEG Signal Classification Using Minimally Random Convolutional Kernel Transform and Hybrid Deep Learning
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
• Rotation Invariance Neural Network
• Class-incremental Learning with Rectified Feature-Graph Preservation
• Using Capsule Neural Network to predict Tuberculosis in lens-free microscopic images
• Distillation of a tractable model from the VQ-VAE
• CbLDM: A Diffusion Model for recovering nanostructure from atomic pair distribution function
• An Ensemble Noise-Robust K-fold Cross-Validation Selection Method for Noisy Labels
• A general framework for defining and optimizing robustness
• Towards Out-Of-Distribution Generalization: A Survey
• Performance evaluation of an integrated photonic convolutional neural network based on delay buffering and wavelength division multiplexing
• EVA-02: A visual representation for neon genesis
• The Limitations of Deep Learning in Adversarial Settings
• SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
• Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block
• Lung cancer identification: a review on detection and classification
• Learning by training: emergent return-point memory from cyclically tuning disordered sphere packings
• PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation
• FedCCEA : A Practical Approach of Client Contribution Evaluation for Federated Learning
• ART: Adaptive Resampling-based Training for Imbalanced Classification
• Deep Learning on Image Denoising: An overview
• Improving the Interpretability of Deep Neural Networks with Knowledge Distillation
• Implicit Sparse Code Hashing
• Low Power Approximate Multiplier Architecture for Deep Neural Networks
• Real-time imaging through dynamic scattering media enabled by fixed optical modulations
• Domain Attention Consistency for Multi-Source Domain Adaptation
• Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks
• SynDelay: A Synthetic Dataset for Delivery Delay Prediction
• Generative Latent Space Dynamics of Electron Density
• Bayesian perspectives for quantum states and application to ab initio quantum chemistry
• Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR
• Semantic Classification of Tabular Datasets via Character-Level Convolutional Neural Networks
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Why flatness does and does not correlate with generalization for deep neural networks
• Learning with Rethinking: Recurrently Improving Convolutional Neural Networks through Feedback
• Optimization Variance: Exploring Generalization Properties of DNNs
• Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Guess-and-Learn (G&amp;L): Measuring the Cumulative Error Cost of Cold-Start Adaptation
• Complementary-Label Learning for Arbitrary Losses and Models
• What made you do this? Understanding black-box decisions with sufficient\n input subsets
• QuadricSLAM: Dual Quadrics from Object Detections as Landmarks in\n Object-oriented SLAM
• Protection Against Reconstruction and Its Applications in Private Federated Learning
• Rethinking Layer-wise Model Merging through Chain of Merges
• Associative Domain Adaptation
• Regularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation
• Improving Dermoscopic Image Segmentation with Enhanced Convolutional-Deconvolutional Networks
• Good Semi-supervised Learning that Requires a Bad GAN
• Controllable Invariance through Adversarial Feature Learning
• Convolutional Neural Fabrics
• Deep Feature Mining via Attention-based BiLSTM-GCN for Human Motor Imagery Recognition
• Unbalanced GANs: Pre-training the Generator of Generative Adversarial Network using Variational Autoencoder
• Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
• Multi-level Feature Learning on Embedding Layer of Convolutional\n Autoencoders and Deep Inverse Feature Learning for Image Clustering
• T-ILR: a Neurosymbolic Integration for LTLf
• Estimating Model Uncertainty of Neural Networks in Sparse Information\n Form
• Collective Learning by Ensembles of Altruistic Diversifying Neural Networks
• Learning compact generalizable neural representations supporting perceptual grouping
• Hierarchical Reinforcement Learning for Deep Goal Reasoning: An Expressiveness Analysis
• The Gaussian Transform
• Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization
• VerifyTL: Secure and Verifiable Collaborative Transfer Learning
• Combating Unknown Bias with Effective Bias-Conflicting Scoring and Gradient Alignment
• Online Coreset Selection for Rehearsal-based Continual Learning
• Rapid Mismatch Estimation via Neural Network Informed Variational Inference
• Design of Kernels in Convolutional Neural Networks for Image Classification
• Convolutional Neural Network(CNN/ConvNet) in Stock Price Movement Prediction
• Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
• CoCoL: A Communication Efficient Decentralized Collaborative Method for Multi-Robot Systems
• RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks
• Generalizing Across Domains via Cross-Gradient Training
• PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization
• A Chain Graph Interpretation of Real-World Neural Networks
• Adversarial Boot Camp: label free certified robustness in one epoch
• Improving Adversarial Robustness via Guided Complement Entropy
• Active Learning for Neurosymbolic Program Synthesis
• Owen Sampling Accelerates Contribution Estimation in Federated Learning
• Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines
• Likelihood Ratios for Out-of-Distribution Detection
• Disentanglement for Discriminative Visual Recognition
• Robust Scene Text Recognition with Automatic Rectification
• Learning both Weights and Connections for Efficient Neural Networks
• A Survey on Automated Driving System Testing: Landscapes and Trends
• CoPE: Conditional image generation using Polynomial Expansions
• Implicitly Maximizing Margins with the Hinge Loss
• Evaluation of Sampling Methods for Scatterplots
• Real-time visual tracking by deep reinforced decision making
• Open Source Dataset and Deep Learning Models for Online Digit Gesture Recognition on Touchscreens
• Cross-Domain Few-Shot Learning by Representation Fusion
• Cluster and then Embed: A Modular Approach for Visualization
• Learning from Similarity-Confidence Data
• DeepAtlas: a tool for effective manifold learning
• Quantum-inspired probability metrics define a complete, universal space for statistical learning
• Revisiting Initialization of Neural Networks
• SynthCoder: A Synthetical Strategy to Tune LLMs for Code Completion
• Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
• Beyond flattening: a geometrically principled positional encoding for vision transformers with Weierstrass elliptic functions
• Saddle Hierarchy in Dense Associative Memory
• GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling
• PerceptionNet: A Deep Convolutional Neural Network for Late Sensor\n Fusion
• A Time Attention based Fraud Transaction Detection Framework
• Geo2Vec: Shape- and Distance-Aware Neural Representation of Geospatial Entities
• Classification of Time-Series Images Using Deep Convolutional Neural\n Networks
• DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment
• DeepMerge: Classifying High-redshift Merging Galaxies with Deep Neural Networks
• Real-Time User-Guided Image Colorization with Learned Deep Priors
• Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic\n Circuits
• Systematic evaluation of convolution neural network advances on the Imagenet
• Emerging Semantic Segmentation from Positive and Negative Coarse Label Learning
• Provable Mixed-Noise Learning with Flow-Matching
• WISCA: A Lightweight Model Transition Method to Improve LLM Training via Weight Scaling
• Contour Detection Using Cost-Sensitive Convolutional Neural Networks
• Transfer learning optimization based on evolutionary selective fine tuning
• BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning
• IEA: Inner Ensemble Average within a convolutional neural network
• A Multi-task Deep Network for Person Re-identification
• HEp-2 Cell Image Classification with Deep Convolutional Neural Networks
• Gesture-based Human-robot Interaction for Field Programmable Autonomous Underwater Robots
• Bootstrapping Deep Neural Networks from Approximate Image Processing Pipelines
• Quantifying the Effects of Enforcing Disentanglement on Variational Autoencoders
• Bayesian Interpolants as Explanations for Neural Inferences
• The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
• Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs
• Notes on Deep Learning for NLP
• Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
• Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians
• Minimizing Task-Oriented Age of Information for Remote Monitoring with Pre-Identification
• Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning
• Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples
• SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation
• AFABench: A Generic Framework for Benchmarking Active Feature Acquisition
• FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning
• A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
• Generative Deep Deconvolutional Learning
• Discriminative Noise Robust Sparse Orthogonal Label Regression-based Domain Adaptation
• Enhanced countering adversarial attacks via input denoising and feature restoring
• An Expectation-Maximization Perspective on Federated Learning
• Defeating Catastrophic Forgetting via Enhanced Orthogonal Weights Modification
• Convolutional-network models to predict wall-bounded turbulence from wall quantities
• SVM and ELM: Who Wins? Object Recognition with Deep Convolutional Features from ImageNet
• The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning
• Multiple Instance Detection Network with Online Instance Classifier Refinement
• Unsupervised Two-Stage Anomaly Detection
• Large Batch Training Does Not Need Warmup
• Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
• Extremal learning: extremizing the output of a neural network in regression problems
• Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network
• Cost-aware Multi-objective Bayesian optimisation
• Differentiable Sparsification for Deep Neural Networks
• Computations of optimal transport distance with Fisher information regularization
• CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection
• On Scalable and Efficient Computation of Large Scale Optimal Transport
• Bayesian Optimized Continual Learning with Attention Mechanism
• Importance Weighted Hierarchical Variational Inference
• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• Accurate Image Super-Resolution Using Very Deep Convolutional Networks
• FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
• Color Spike Data Generation via Bio-inspired Neuron-like Encoding with an Artificial Photoreceptor Layer
• Calibrating Biased Distribution in VFM-derived Latent Space via Cross-Domain Geometric Consistency
• Learning in the Machine: the Symmetries of the Deep Learning Channel
• Genuine multipartite entanglement verification with convolutional neural networks
• Traceability of Deep Neural Networks
• DREAMS: Preserving both Local and Global Structure in Dimensionality Reduction
• Domain Adaptation and Image Classification via Deep Conditional Adaptation Network
• Adaptive Hierarchical Hyper-gradient Descent
• Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer
• Generative Adversarial Networks
• Feature Losses for Adversarial Robustness
• Fast Exploration of Weight Sharing Opportunities for CNN Compression
• SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
• Learning to Learn Single Domain Generalization
• Machine Learning, Deep Learning, and Hedonic Methods for Real Estate\n Price Prediction
• A Survey of Black-Box Adversarial Attacks on Computer Vision Models
• Uncertainty Propagation in Deep Neural Network Using Active Subspace
• Stochastic Computing for Hardware Implementation of Binarized Neural Networks
• A Neural-Network Framework for Tracking and Identification of Cosmic-Ray Nuclei in the RadMap Telescope
• Generative Moment Matching Networks
• BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks
• Constraint-Aware Flow Matching via Randomized Exploration
• TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML
• Boosting Image Recognition with Non-differentiable Constraints
• Efficient Online Minimization for Low-Rank Subspace Clustering
• Maximum-Entropy Adversarial Data Augmentation for Improved\n Generalization and Robustness
• Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvature
• Embedding of FRPN in CNN architecture
• Recognizing Handwritten Mathematical Expressions as LaTex Sequences Using a Multiscale Robust Neural Network
• Widening the Network Mitigates the Impact of Data Heterogeneity on FedAvg
• Feature Request Analysis and Processing: Tasks, Techniques, and Trends
• Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference
• Iterative VAE as a predictive brain model for out-of-distribution generalization
• Deep Learning in Multi-organ Segmentation
• Dissecting Hessian: Understanding Common Structure of Hessian in Neural Networks
• Optimal Transport Based Generative Autoencoders
• Wasserstein Distance Guided Cross-Domain Learning
• ViPTT-Net: Video pretraining of spatio-temporal model for tuberculosis type classification from chest CT scans
• Learning with symmetric positive definite matrices via generalized Bures-Wasserstein geometry
• A Sobel-Gradient MLP Baseline for Handwritten Character Recognition
• FAIRVAR: Fair Federated Learning via Variance Regularization
• Learning to Map Sentences to Logical Form: Structured Classification\n with Probabilistic Categorial Grammars
• PCA- and SVM-Grad-CAM for Convolutional Neural Networks: Closed-form Jacobian Expression
• Similarity-based Text Recognition by Deeply Supervised Siamese Network
• The Rise of Generative AI for Metal-Organic Framework Design and Synthesis
• An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation
• CrypTen: Secure Multi-Party Computation Meets Machine Learning
• Feature Learning by Multidimensional Scaling and its Applications in Object Recognition
• Dense Transformer Networks
• Fast Prediction with SVM Models Containing RBF Kernels
• Activate Me!: Designing Efficient Activation Functions for Privacy-Preserving Machine Learning with Fully Homomorphic Encryption
• Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
• Learning to Predict Trustworthiness with Steep Slope Loss
• NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
• FedNS: Improving Federated Learning for collaborative image classification on mobile clients
• Adaptive Neighbourhoods for the Discovery of Adversarial Examples
• Adma: A Flexible Loss Function for Neural Networks
• Application of Computer Vision Techniques for Segregation of PlasticWaste based on Resin Identification Code
• Robust Tracking Using Region Proposal Networks
• Dynamic Differential-Privacy Preserving SGD
• Beyond Neighbourhood-Preserving Transformations for Quantization-Based Unsupervised Hashing
• Novel Framework for Spectral Clustering using Topological Node\n Features(TNF)
• Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks
• Classifying neuromorphic data using a deep learning framework for image\n classification
• Introducing the Simulated Flying Shapes and Simulated Planar Manipulator\n Datasets
• Conic Formulations of Transport Metrics for Unbalanced Measure Networks and Hypernetworks
• Blockchain Assisted Decentralized Federated Learning (BLADE-FL) with Lazy Clients
• A Study of Deep Learning Robustness Against Computation Failures
• SoK: Data Minimization in Machine Learning
• Elimination of All Bad Local Minima in Deep Learning
• Lameness detection in dairy cows using pose estimation and bidirectional LSTMs
• Rethink ReLU to Training Better CNNs
• Multi-Task Kernel Null-Space for One-Class Classification
• A Deep Learning based Signal Dimension Estimator with Single Snapshot Signal in Phased Array Radar Application
• Auto-ML Deep Learning for Rashi Scripts OCR
• Deep Sparse Subspace Clustering
• Facial Keypoints Detection
• Dirichlet Pruning for Neural Network Compression
• The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures
• Measuring the tendency of CNNs to Learn Surface Statistical Regularities
• Lifted Relational Neural Networks
• Object-based Metamorphic Testing through Image Structuring
• Toward the quantification of cognition
• Reverse Convolution and Its Applications to Image Restoration
• Automated Segmentation of Coronal Brain Tissue Slabs for 3D Neuropathology
• Efficient Neural Network Implementation with Quadratic Neuron
• Gaussian Process Bandit Optimization of the Thermodynamic Variational\n Objective
• Adversarial Training for EM Classification Networks
• Swift for TensorFlow: A portable, flexible platform for deep learning
• Ensemble Learning with Manifold-Based Data Splitting for Noisy Label Correction
• Context Encoding for Semantic Segmentation
• Towards Shape Biased Unsupervised Representation Learning for Domain Generalization
• How benign is benign overfitting?
• ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks
• Fast Haar Transforms for Graph Neural Networks
• Character-level Convolutional Network for Text Classification Applied to Chinese Corpus
• Learning Spatial Decay for Vision Transformers
• MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AI
• General Probabilistic Surface Optimization and Log Density Estimation
• Improving Accuracy of Binary Neural Networks using Unbalanced Activation Distribution
• Dual-stream Network for Visual Recognition
• A Closer Look at Reference Learning for Fourier Phase Retrieval
• Continual Learning in Neural Networks
• bigMap: Big Data Mapping with Parallelized t-SNE
• Learning with a Strong Adversary
• Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey
• Resource-Aware Aggregation and Sparsification in Heterogeneous Ensemble Federated Learning
• Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
• Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability
• Enhanced Variational Inference with Dyadic Transformation
• AI-Skin : Skin Disease Recognition based on Self-learning and Wide Data Collection through a Closed Loop Framework
• Towards Robust Active Feature Acquisition
• Incoherent Light-Driven Nonlinear Optical Extreme Learner via Data Reverberation
• Defending Adversarial Attacks via Semantic Feature Manipulation
• Learning Deep Features via Congenerous Cosine Loss for Person Recognition
• Flexible Dataset Distillation: Learn Labels Instead of Images
• Π-nets: Deep Polynomial Neural Networks
• Calculating the Projective Norm of higher-order tensors using a gradient descent algorithm
• Softmax-based Classification is k-means Clustering: Formal Proof, Consequences for Adversarial Attacks, and Improvement through Centroid Based Tailoring
• A software engineering perspective on engineering machine learning systems: State of the art and challenges
• Interpretable CNNs for Object Classification
• Understanding the Limitations of Variational Mutual Information Estimators
• Dual-stream Maximum Self-attention Multi-instance Learning
• Neural Tangent Knowledge Distillation for Optical Convolutional Networks
• OFAL: An Oracle-Free Active Learning Framework
• Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
• On the Effectiveness of Defensive Distillation
• Lightning Prediction under Uncertainty: DeepLight with Hazy Loss
• A Spin Glass Characterization of Neural Networks
• A State Aggregation Approach for Solving Knapsack Problem with Deep Reinforcement Learning
• Keyword Mamba: Spoken Keyword Spotting with State Space Models
• An Experimental Exploration of In-Memory Computing for Multi-Layer Perceptrons
• A Bayesian Data Augmentation Approach for Learning Deep Models
• A Trace-restricted Kronecker-Factored Approximation to Natural Gradient
• QuProFS: An Evolutionary Training-free Approach to Efficient Quantum Feature Map Search
• Guiding Optimizations with Meliora: A Deep Walk down Memory Lane
• Data-Efficient Neural Training with Dynamic Connectomes
• Label Inference Attacks against Federated Unlearning
• Structure-Preserving Digital Twins via Conditional Neural Whitney Forms
• DSperse: A Framework for Targeted Verification in Zero-Knowledge Machine Learning
• Deep Learning for Single-View Instance Recognition
• Confounder Identification-free Causal Visual Feature Learning
• Machine learning in next-generation AEM fuel cells: a systematic review
• The Robust Manifold Defense: Adversarial Training using Generative Models
• Metric Learning for Novelty and Anomaly Detection
• Compression of Deep Neural Networks on the Fly
• Lung sounds classification using convolutional neural networks
• QUOTIENT: Two-Party Secure Neural Network Training and Prediction
• apricot: Submodular selection for data summarization in Python
• HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules
• Adaptive Weight Decay for Deep Neural Networks
• IWA: Integrated Gradient based White-box Attacks for Fooling Deep Neural Networks
• Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences
• Mean Nyström Embeddings for Adaptive Compressive Learning
• Edge-featured Graph Neural Architecture Search
• Decorrelated feature importance from local sample weighting
• ASAudio: A Survey of Advanced Spatial Audio Research
• Re-evaluating Evaluation
• Non-omniscient backdoor injection with a single poison sample: Proving the one-poison hypothesis for linear regression and linear classification
• Task complexity shapes internal representations and robustness in neural networks
• A Proximal Approach for Sparse Multiclass SVM
• Cumulative Learning Rate Adaptation: Revisiting Path-Based Schedules for SGD and Adam
• ASkDAgger: Active Skill-level Data Aggregation for Interactive Imitation Learning
• HFedATM: Hierarchical Federated Domain Generalization via Optimal Transport and Regularized Mean Aggregation
• Learning from Similarity-Confidence and Confidence-Difference
• Integrated Influence: Data Attribution with Baseline
• ULU: A Unified Activation Function
• Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
• Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization
• Self-Error Adjustment: Theory and Practice of Balancing Individual Performance and Diversity in Ensemble Learning
• The use of physics-informed neural network approach to image restoration via nonlinear PDE tools
• Toward Errorless Training ImageNet-1k
• ALScope: A Unified Toolkit for Deep Active Learning
• Deep Distillation Gradient Preconditioning for Inverse Problems
• Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
• Grid-like Error-Correcting Codes for Matrix Multiplication with Better Correcting Capability
• Compressing Large Language Models with PCA Without Performance Loss
• SelectiveShield: Lightweight Hybrid Defense Against Gradient Leakage in Federated Learning
• Self-paced Data Augmentation for Training Neural Networks
• Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
• Evaluating Selective Encryption Against Gradient Inversion Attacks
• Unsupervised Pairwise Learning Optimization Framework for Cross-Corpus EEG-Based Emotion Recognition Based on Prototype Representation
• SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios
• Slice or the Whole Pie? Utility Control for AI Models
• von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification
• Training Sparse Neural Networks
• Universal Convexification via Risk-Aversion
• Deep learning framework for crater detection and identification on the Moon and Mars
• Prediction-Oriented Subsampling from Data Streams
• Training Deep Neural Networks via Branch-and-Bound
• Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
• A Fourier-based Framework for Domain Generalization
• Channel Coding for Unequal Error Protection in Digital Semantic Communication
• GaitAdapt: Continual Learning for Evolving Gait Recognition
• LocalNorm: Robust Image Classification through Dynamically Regularized Normalization
• DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification
• A Non-Technical Survey on Deep Convolutional Neural Network Architectures
• On Target Segmentation for Direct Speech Translation
• Blind Image Restoration with Flow Based Priors
• Improved Robustness to Open Set Inputs via Tempered Mixup
• RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging
• GEDAN: Learning the Edit Costs for Graph Edit Distance
• A Markov Decision Process Approach to Active Meta Learning
• An Experimental Study of Semantic Continuity for Deep Learning Models
• A Biologically Plausible Learning Rule for Deep Learning in the Brain
• On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach
• Multi-Objective Pruning for CNNs Using Genetic Algorithm
• Domain Adaptation with Incomplete Target Domains
• Automatic deep learning for trend prediction in time series data
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Learned versus Hand-Designed Feature Representations for 3d Agglomeration
• Chinese Embedding via Stroke and Glyph Information: A Dual-channel View
• A Generative Model for Sampling High-Performance and Diverse Weights for\n Neural Networks
• meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting
• Disentangling Factors of Variation by Mixing Them
• FedAPTA: Federated Multi-task Learning for Heterogeneous Devices with Adaptive Layer-wise Pruning and Task-aware Aggregation
• Reservoir Computing with Evolved Critical Neural Cellular Automata
• Modular Transformer Architecture for Precision Agriculture Imaging
• DySTop
• Deep Feature-specific Imaging
• Deep Learning Face Representation by Joint Identification-Verification
• SpectraLLM: Uncovering the Ability of LLMs for Molecular Structure Elucidation from Multi-Spectral Data
• Model-Agnostic Dynamic Feature Selection with Uncertainty Quantification
• Versatile yet Efficient Network Traffic Analysis: Offloading Network Foundation Model to SmartNIC
• Defending Against Adversarial Attacks Using Random Forests
• Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning
• Stochastic Encodings for Active Feature Acquisition
• Accumulative Poisoning Attacks on Real-time Data
• A Machine Learning Approach to Routing
• Pulse Shape Discrimination Algorithms: Survey and Benchmark
• Discrete Rotation Equivariance for Point Cloud Recognition
• Multi-vision Attention Networks for On-line Red Jujube Grading
• An Efficient Deep Learning Technique for the Navier-Stokes Equations: Application to Unsteady Wake Flow Dynamics
• Conceptual Domain Adaptation Using Deep Learning
• RouteMark: A Fingerprint for Intellectual Property Attribution in Routing-based Model Merging
• RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs
• FASTER Recurrent Networks for Efficient Video Classification
• Increasing the Generalisation Capacity of Conditional VAEs
• Training Deep Neural Networks by optimizing over nonlocal paths in\n hyperparameter space
• Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification
• Learning to Disentangle Robust and Vulnerable Features for Adversarial Detection
• Defending Against Beta Poisoning Attacks in Machine Learning Models
• Randomized algorithms for the low multilinear rank approximations of tensors
• Imbalanced Deep Learning by Minority Class Incremental Rectification
• FedGuard: A Diverse-Byzantine-Robust Mechanism for Federated Learning with Major Malicious Clients
• Towards Quantifying Intrinsic Generalization of Deep ReLU Networks
• Comparison Based Nearest Neighbor Search
• Sparse Representation-based Open Set Recognition
• DD-DeepONet: Domain decomposition and DeepONet for solving partial differential equations in three application scenarios
• Segmenting proto-halos with vision transformers
• Max-Mahalanobis Linear Discriminant Analysis Networks
• Interpretable Deep Convolutional Neural Networks via Meta-learning
• Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-level
• Fusion of Pervasive RF Data with Spatial Images via Vision Transformers for Enhanced Mapping in Smart Cities
• Collaborative creativity with Monte-Carlo Tree Search and Convolutional Neural Networks
• Source Separation with Deep Generative Priors
• Flow Contrastive Estimation of Energy-Based Models
• Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency
• Fast Subspace Clustering Based on the Kronecker Product
• Universum Prescription: Regularization using Unlabeled Data
• Initialization Using Perlin Noise for Training Networks with a Limited Amount of Data
• On the consistency of Fr 'echet means in deformable models for curve and\n image analysis
• Evaluating the Dynamics of Membership Privacy in Deep Learning
• Efficient Machine Unlearning via Influence Approximation
• Recurrent Flow-Guided Semantic Forecasting
• Unifying and Merging Well-trained Deep Neural Networks for Inference Stage
• Consistent Representation Learning for High Dimensional Data Analysis
• Generating Artificial Data for Private Deep Learning
• CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals
• SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
• Efficient Hierarchical Clustering for Classification and Anomaly Detection
• Multi-Task Neural Processes
• Predicting Drug Interactions and Mutagenicity with Ensemble Classifiers on Subgraphs of Molecules
• Do We Need Zero Training Loss After Achieving Zero Training Error?
• Differentially private k-means clustering via exponential mechanism and max cover
• Topological Detection of Trojaned Neural Networks
• Listening to the Unspoken: Exploring "365" Aspects of Multimodal Interview Performance Assessment
• A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
• Agentic Privacy-Preserving Machine Learning
• Unsupervised learning of digit recognition using spike-timing-dependent plasticity. [europepmc]
• Training Deep Spiking Neural Networks Using Backpropagation. [europepmc]
• Low-dose CT via convolutional neural network. [europepmc]
• A Deep Learning-Based Radiomics Model for Prediction of Survival in Glioblastoma Multiforme. [europepmc]
• Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. [europepmc]
• Towards deep learning with segregated dendrites. [europepmc]
• Reservoir computing using dynamic memristors for temporal information processing. [europepmc]
• VAMPnets for deep learning of molecular kinetics. [europepmc]
• Deep Learning for Computer Vision: A Brief Review. [europepmc]
• Artificial intelligence in healthcare: past, present and future. [europepmc]
• Super-resolution musculoskeletal MRI using deep learning. [europepmc]
• Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks. [europepmc]
• Efficient and self-adaptive in-situ learning in multilayer memristor neural networks. [europepmc]
• Neuromorphic computing with multi-memristive synapses. [europepmc]
• Artificial optic-neural synapse for colored and color-mixed pattern recognition. [europepmc]
• Tooth detection and numbering in panoramic radiographs using convolutional neural networks. [europepmc]
• Going Deeper in Spiking Neural Networks: VGG and Residual Architectures. [europepmc]
• SPHIRE-crYOLO is a fast and accurate fully automated particle picker for cryo-EM. [europepmc]
• Brain age prediction using deep learning uncovers associated sequence variants. [europepmc]
• CatBoost for big data: an interdisciplinary review. [europepmc]
• Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models. [europepmc]
• Convolutional neural networks in medical image understanding: a survey. [europepmc]
• Machine Learning: Algorithms, Real-World Applications and Research Directions. [europepmc]
• Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. [europepmc]
• Transfer learning for medical image classification: a literature review. [europepmc]

Related

• Handwritten Character Recognition Using Unique Feature Extraction\n Technique
• Fully Convolutional Networks for Handwriting Recognition
• Handwritten Text Recognition Using Convolutional Neural Network
• A Sobel-Gradient MLP Baseline for Handwritten Character Recognition
• An MLP Baseline for Handwriting Recognition Using Planar Curvature and Gradient Orientation