The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]

2012/10/19 by Li Deng · 180 citations
Computer Science · #Handwritten Text Recognition Techniques #Advanced Neural Network Applications #Advanced Image and Video Retrieval Techniques

paper · doi:10.1109/msp.2012.2211477

Abstract

In this issue, “Best of the Web” presents the modified National Institute of Standards and Technology (MNIST) resources, consisting of a collection of handwritten digit images used extensively in optical character recognition and machine learning research.

Citations

• Gradient-based learning applied to document recognition

Cited by

• Design Challenges of Neural Network Acceleration Using Stochastic\n Computing
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations
• ABC-FL: Anomalous and Benign client Classification in Federated Learning
• Sensor movement drives emergent attention and scalability in active neural cellular automata
• Quantum optical reservoir computing powered by boson sampling
• Multi-scale Autoregressive Models are Laplacian, Discrete, and Latent Diffusion Models in Disguise
• Express Wavenet: A lower parameter optical neural network with random shift wavelet pattern
• HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep\n Spiking Neural Networks by Training with Crafted Input Noise
• High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
• Solving Interpretable Kernel Dimension Reduction
• SVGD: A Virtual Gradients Descent Method for Stochastic Optimization
• ZORB: A Derivative-Free Backpropagation Algorithm for Neural Networks
• A Study on the Uncertainty of Convolutional Layers in Deep Neural Networks
• Task allocation for decentralized training in heterogeneous environment
• Lipschitz-aware Linearity Grafting for Certified Robustness
• Score-based constrained generative modeling via Langevin diffusions with boundary conditions
• Coupled Flow Matching
• OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation
• VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set
• Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models
• Fast and Compact Tsetlin Machine Inference on CPUs Using Instruction-Level Optimization
• Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
• Brain-Inspired Perspective on Configurations: Unsupervised Similarity and Early Cognition
• HAMLOCK: HArdware-Model LOgically Combined attacK
• MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network
• Rethinking PCA Through Duality
• Exploration via Feature Perturbation in Contextual Bandits
• Benchmarking Out-of-Distribution Detection for Plankton Recognition: A Systematic Evaluation of Advanced Methods in Marine Ecological Monitoring
• Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation
• Closing the Curvature Gap: Full Transformer Hessians and Their Implications for Scaling Laws
• One-Bit Quantization for Random Features Models
• Sample-Aware Knowledge Association and Enhancement for Open-Vocabulary Continual Learning
• The Intrinsic Dimension of Images and Its Impact on Learning
• Hybrid Boson Sampling-Neural Network Architecture for Enhanced Classification
• nuGPR: GPU-Accelerated Gaussian Process Regression with Iterative Algorithms and Low-Rank Approximations
• Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
• Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation
• Towards Distribution-Shift Uncertainty Estimation for Inverse Problems with Generative Priors
• A Unified Zeroth-Order Optimization Framework via Oblivious Randomized Sketching
• Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
• FML-bench: A Benchmark for Automatic ML Research Agents Highlighting the Importance of Exploration Breadth
• Private Federated Multiclass Post-hoc Calibration
• HeunNet: Extending ResNet using Heun's Methods
• Incentivizing Time-Aware Fairness in Data Sharing
• Towards Neurocognitive-Inspired Intelligence: From AI's Structural Mimicry to Human-Like Functional Cognition
• Theoretical guarantees for change localization using conformal p-values
• Some theoretical improvements on the tightness of PAC-Bayes risk certificates for neural networks
• Optimal Stopping in Latent Diffusion Models
• A taxonomy of interpretation and explanation methods for capsule network architectures
• Rethinking Nonlinearity: Trainable Gaussian Mixture Modules for Modern Neural Architectures
• BuilderBench -- A benchmark for generalist agents
• Field Free Spin-Orbit Torque Controlled Synapse and Stochastic Neuron Devices for Spintronic Boltzmann Neural Networks
• Efficient Manifold-Constrained Neural ODE for High-Dimensional Datasets
• PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networks
• Cellular Learning: Scattered Data Regression in High Dimensions via Voronoi Cells
• Using Fourier Analysis and Mutant Clustering to Accelerate DNN Mutation Testing
• Quantum-inspired Benchmark for Estimating Intrinsic Dimension
• Temporal Score Rescaling for Temperature Sampling in Diffusion and Flow Models
• Random Feature Spiking Neural Networks
• Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties
• SVDefense: Effective Defense against Gradient Inversion Attacks via Singular Value Decomposition
• Ultra-Efficient Decoding for End-to-End Neural Compression and Reconstruction
• Stealing AI Model Weights Through Covert Communication Channels
• Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring
• Improved Stochastic Optimization of LogSumExp
• RDD: Pareto Analysis of the Rate-Distortion-Distinguishability Trade-off
• PEARL: Performance-Enhanced Aggregated Representation Learning
• Learning-Based Testing for Deep Learning: Enhancing Model Robustness with Adversarial Input Prioritization
• Deep Learning for Fluorescence Lifetime Predictions Enables High-Throughput In Vivo Imaging
• Interpreting Deep Learning: The Machine Learning Rorschach Test?
• Multidimensional Uncertainty Quantification via Optimal Transport
• QuFoundry: Generating Data with Quantum Properties for Quantum Machine Learning Utility
• Contrastive Mutual Information Learning: Toward Robust Representations without Positive-Pair Augmentations
• Score-based Idempotent Distillation of Diffusion Models
• Distribution-Controlled Client Selection to Improve Federated Learning Strategies
• LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training
• A Recovery Guarantee for Sparse Neural Networks
• Bispectral OT: Dataset Comparison using Symmetry-Aware Optimal Transport
• Aligning Inductive Bias for Data-Efficient Generalization in State Space Models
• Sparse Representations Improve Adversarial Robustness of Neural Network Classifiers
• The Unwinnable Arms Race of AI Image Detection
• Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation
• MMG: Mutual Information Estimation via the MMSE Gap in Diffusion
• The role of fibration symmetries in geometric deep learning
• Results of the Protein Engineering Tournament: An Open Science Benchmark for Protein Modeling and Design
• The specious art of single-cell genomics
• Integrating Stacked Intelligent Metasurfaces and Power Control for Dynamic Edge Inference via Over-The-Air Neural Networks
• Shared-Weights Extender and Gradient Voting for Neural Network Expansion
• Efficient Reinforcement Learning by Reducing Forgetting with Elephant Activation Functions
• Multi-Worker Selection based Distributed Swarm Learning for Edge IoT with Non-i.i.d. Data
• All-magnonic neurons for analog artificial neural networks
• Fine-Tuning Robot Policies While Maintaining User Privacy
• SPRINT: Stochastic Performative Prediction With Variance Reduction
• An Unlearning Framework for Continual Learning
• Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification
• Morphological Cognition: Classifying MNIST Digits Through Morphological Computation Alone
• Jim137/qkan: v0.1.0
• A biological vision inspired framework for machine perception of abutting grating illusory contours
• Free-riders in Federated Learning: Attacks and Defenses
• Exploring Training Data Attribution under Limited Access Constraints
• Reconciling Communication Compression and Byzantine-Robustness in Distributed Learning
• Optimizing Neural Networks with Learnable Non-Linear Activation Functions via Lookup-Based FPGA Acceleration
• Solving ill-conditioned polynomial equations using score-based priors with application to multi-target detection
• Gradients, parallelism, and variance of quantum estimates
• CogGNN: Cognitive Graph Neural Networks in Generative Connectomics
• Multiscaling in Wasserstein Spaces
• FedRP: A Communication-Efficient Approach for Differentially Private Federated Learning Using Random Projection
• Pareto-optimal Tradeoffs Between Communication and Computation with Flexible Gradient Tracking
• ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
• Locality in Image Diffusion Models Emerges from Data Statistics
• CAGFuzz: Coverage-Guided Adversarial Generative Fuzzing Testing of Deep Learning Systems
• Uncertainty Awareness and Trust in Explainable AI- On Trust Calibration using Local and Global Explanations
• ForTIFAI: Fending Off Recursive Training Induced Failure for AI Model Collapse
• Heart Disease Prediction: A Comparative Study of Optimisers Performance in Deep Neural Networks
• InJecteD: Analyzing Trajectories and Drift Dynamics in Denoising Diffusion Probabilistic Models for 2D Point Cloud Generation
• ACE and Diverse Generalization via Selective Disagreement
• Classical Neural Networks on Quantum Devices via Tensor Network Disentanglers: A Case Study in Image Classification
• Towards Visually Explaining Variational Autoencoders
• DeepPoison: Feature Transfer Based Stealthy Poisoning Attack
• SeisBench—A Toolbox for Machine Learning in Seismology
• SpecNet: Spectral Domain Convolutional Neural Network
• Can VLMs Recall Factual Associations From Visual References?
• RL's Razor: Why Online Reinforcement Learning Forgets Less
• DRtool: An Interactive Tool for Analyzing High-Dimensional Clusterings
• Ordinal Adaptive Correction: A Data-Centric Approach to Ordinal Image Classification with Noisy Labels
• Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function
• SAPAG: A Self-Adaptive Privacy Attack From Gradients
• Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing
• High-resolution single-pixel imaging in real time with iterative or deep learning-based reconstruction enhancement
• Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models
• UniMLR: Modeling Implicit Class Significance for Multi-Label Ranking
• Meta-Learning Strategies through Value Maximization in Neural Networks
• Class Incremental Continual Learning with Self-Organizing Maps and Variational Autoencoders Using Synthetic Replay
• Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
• Probability Density from Latent Diffusion Models for Out-of-Distribution Detection
• Towards stable AI systems for Evaluating Arabic Pronunciations
• Mini-Batch Robustness Verification of Deep Neural Networks
• Tackling Federated Unlearning as a Parameter Estimation Problem
• Responsible Artificial Intelligence for Earth Observation: Achievable and realistic paths to serve the collective good
• Information Templates: A New Paradigm for Intelligent Active Feature Acquisition
• Language-Guided Tuning: Enhancing Numeric Optimization with Textual Feedback
• Wormhole Dynamics in Deep Neural Networks
• When Secure Aggregation Falls Short: Achieving Long-Term Privacy in Asynchronous Federated Learning for LEO Satellite Networks
• SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360\n degree Images
• Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
• SimQFL: A Quantum Federated Learning Simulator with Real-Time Visualization
• Toward Architecture-Agnostic Local Control of Posterior Collapse in VAEs
• Combinations of Fast Activation and Trigonometric Functions in Kolmogorov-Arnold Networks
• Multi-Sensory Cognitive Computing for Learning Population-level Brain Connectivity
• Detecting Untargeted Attacks and Mitigating Unreliable Updates in Federated Learning for Underground Mining Operations
• ConFoc: Content-Focus Protection Against Trojan Attacks on Neural Networks
• Exploring Cross-Stage Adversarial Transferability in Class-Incremental Continual Learning
• Towards Scalable Lottery Ticket Networks using Genetic Algorithms
• Incoherent Light-Driven Nonlinear Optical Extreme Learner via Data Reverberation
• Simulation of Charge Stability Diagrams for Automated Tuning Solutions (SimCATS)
• Designing with Deception: ML- and Covert Gate-Enhanced Camouflaging to Thwart IC Reverse Engineering
• When and how can inexact generative models still sample from the data manifold?
• Separation and Collaboration: Two-Level Routing Grouped Mixture-of-Experts for Multi-Domain Continual Learning
• Strategic Incentivization for Locally Differentially Private Federated Learning
• Watermarking Kolmogorov-Arnold Networks for Emerging Networked Applications via Activation Perturbation
• Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling
• Non-Determinism in Neural Networks for Adversarial Robustness
• Deep Distillation Gradient Preconditioning for Inverse Problems
• Likelihood Matching for Diffusion Models
• Zero-Variance Gradients for Variational Autoencoders
• Pigeon-SL: Robust Split Learning Framework for Edge Intelligence under Malicious Clients
• A Trainable Optimizer
• Improving Noise Efficiency in Privacy-preserving Dataset Distillation
• MiraGe: Multimodal Discriminative Representation Learning for Generalizable AI-Generated Image Detection
• HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses
• Random Walk Learning and the Pac-Man Attack
• Graph Lineages and Skeletal Graph Products
• Federated Learning on Riemannian Manifolds: A Gradient-Free Projection-Based Approach
• COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
• Density Operator Expectation Maximization
• Improving Neural Network Training using Dynamic Learning Rate Schedule for PINNs and Image Classification
• Probabilistic Consistency in Machine Learning and Its Connection to Uncertainty Quantification
• Reservoir Computation with Networks of Differentiating Neuron Ring Oscillators
• Clustering by Attention: Leveraging Prior Fitted Transformers for Data Partitioning
• Machine Learning enabled Spectrum Sharing in Dense LTE-U/Wi-Fi\n Coexistence Scenarios

Related

• EMNIST: an extension of MNIST to handwritten letters
• Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs
• Massively Deep Artificial Neural Networks for Handwritten Digit Recognition
• Comparison and Combination of State-of-the-art Techniques for Handwritten Character Recognition: Topping the MNIST Benchmark
• Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)