Neural Architecture Search with Reinforcement Learning
2016/11/05 by Barret Zoph, Quoc V. Le, Zoph, Barret +1 · 1 voice · 350 citations
Computer Science · #Machine Learning and Data Classification #Anomaly Detection Techniques and Applications #Neural Networks and Applications
paper · pdf · doi:10.48550/arxiv.1611.01578
Abstract
Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy. Our CIFAR-10 model achieves a test error rate of 3.65, which is 0.09 percent better and 1.05x faster than the previous state-of-the-art model that used a similar architectural scheme. On the Penn Treebank dataset, our model can compose a novel recurrent cell that outperforms the widely-used LSTM cell, and other state-of-the-art baselines. Our cell achieves a test set perplexity of 62.4 on the Penn Treebank, which is 3.6 perplexity better than the previous state-of-the-art model. The cell can also be transferred to the character language modeling task on PTB and achieves a state-of-the-art perplexity of 1.214.
Citations
Cited by
- FlowBot: Inducing LLM Workflows with Bilevel Optimization and Textual Gradients
- Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks
- Automated Reinforcement Learning: An Overview
- NeuronSoup: Evolving Asynchronous, Shared-Neuron Temporal Graphs without Backpropagation
- Scaling Closed-Loop Feature Channel Configuration with LLMs
- Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive science
- Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
- AlphaGo Moment for Model Architecture Discovery
- Discovering Sparse Recovery Algorithms Using Neural Architecture Search
- Rethinking Output Alignment For 1-bit Post-Training Quantization of Large Language Models
- Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
- Surrogate Neural Architecture Codesign Package (SNAC-Pack)
- Dynamic Rank Reinforcement Learning for Adaptive Low-Rank Multi-Head Self Attention in Large Language Models
- GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search
- Optimized Architectures for Kolmogorov-Arnold Networks
- Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning
- Learning When to Switch: Adaptive Policy Selection via Reinforcement Learning
- Rep Smarter, Not Harder: AI Hypertrophy Coaching with Wearable Sensors and Edge Neural Networks
- Network of Theseus (like the ship)
- Neural Architecture Search of Time-to-First-Spike-Coded Spiking Neural Networks for Efficient Eye-based Emotion Recognition
- Efficient Hyperparameter Search for Non-Stationary Model Training
- BioArc: Discovering Optimal Neural Architectures for Biological Foundation Models
- LLM-Driven Transient Stability Assessment: From Automated Simulation to Neural Architecture Design
- Efficient Robot Design with Multi-Objective Black-Box Optimization and Large Language Models
- Parameter Aware Mamba Model for Multi-task Dense Prediction
- Efficiently Training A Flat Neural Network Before It has been Quantizated
- Progressive Neural Architecture Search
- N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning
- RF-DETR: Neural Architecture Search for Real-Time Detection Transformers
- H-Model: Dynamic Neural Architectures for Adaptive Processing
- PP-LCNet: A Lightweight CPU Convolutional Neural Network
- RMM: Reinforced Memory Management for Class-Incremental Learning
- FasterSeg: Searching for Faster Real-time Semantic Segmentation
- Models Got Talent: Identifying High Performing Wearable Human Activity Recognition Models Without Training
- MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
- Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
- A Review of Bilevel Optimization: Methods, Emerging Applications, and Recent Advancements
- SMASH: One-Shot Model Architecture Search through HyperNetworks
- SNAS: Stochastic Neural Architecture Search
- Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
- Explaining Transition Systems through Program Induction
- Branched Multi-Task Networks: Deciding What Layers To Share
- D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
- Dynamic Convolution: Attention over Convolution Kernels
- FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
- Evolutionary Architecture Search for Graph Neural Networks
- Meta-learning curiosity algorithms
- Generalization Guarantees for Neural Architecture Search with\n Train-Validation Split
- Improving the sample-efficiency of neural architecture search with reinforcement learning
- Fixed Priority Global Scheduling from a Deep Learning Perspective
- NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
- Contrastive Embeddings for Neural Architectures
- Object Detection in 20 Years: A Survey
- On-Policy Model Errors in Reinforcement Learning
- Neural Architecture Search for Traffic Prediction: A Survey of Methods, Challenges, and Future Directions
- Exploiting the Potential of Standard Convolutional Autoencoders for\n Image Restoration by Evolutionary Search
- AutoML to Date and Beyond: Challenges and Opportunities
- Learning Architectures for Binary Networks
- Do CNNs Encode Data Augmentations?
- Deep Multimodal Learning: A Survey on Recent Advances and Trends
- Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
- Fine-Grained Neural Architecture Search
- DARC: Differentiable ARchitecture Compression
- SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions
- URNet : User-Resizable Residual Networks with Conditional Gating Module
- Encoder-Decoder Neural Architecture Optimization for Keyword Spotting
- μNAS: Constrained Neural Architecture Search for Microcontrollers
- Policy-GNN: Aggregation Optimization for Graph Neural Networks
- Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
- Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing
- A Survey of Model Compression and Acceleration for Deep Neural Networks
- fPINNs: Fractional Physics-Informed Neural Networks
- Recent Advances in Neural Program Synthesis
- Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation
- MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Server
- PAMS: Quantized Super-Resolution via Parameterized Max Scale
- Deep Active Learning with a Neural Architecture Search
- Evolutionary Neural Architecture Search for Retinal Vessel Segmentation
- Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
- RepVGG: Making VGG-style ConvNets Great Again
- Dynamic Optimization of Neural Network Structures Using Probabilistic Modeling
- Densely Connected Search Space for More Flexible Neural Architecture Search
- BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
- Balancing Accuracy and Latency in Multipath Neural Networks
- Graph Pruning for Model Compression
- SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System
- Rethinking the Number of Channels for the Convolutional Neural Network
- Multiresolution Convolutional Autoencoders
- Video Action Recognition Via Neural Architecture Searching
- Deeper Insights into Weight Sharing in Neural Architecture Search
- Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
- Regime-Adaptive Bayesian Optimization via Dirichlet Process Mixtures of Gaussian Processes
- Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures
- Automated Machine Learning: State-of-The-Art and Open Challenges
- A Study on Inference Latency for Vision Transformers on Mobile Devices
- RC-DARTS: Resource Constrained Differentiable Architecture Search
- Adversarial Policy Gradient for Deep Learning Image Augmentation
- Evaluating Efficient Performance Estimators of Neural Architectures
- Autonomous construction of parameterizable 3D leaf models from scanned sweet pepper leaves with deep generative networks
- New Perspective of Interpretability of Deep Neural Networks
- Transfer Learning for Multi-lingual Tasks -- a Survey
- On the Anisotropy of Score-Based Generative Models
- Neural Architecture Search for global multi-step Forecasting of Energy Production Time Series
- TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning
- BlockQNN: Efficient Block-wise Neural Network Architecture Generation
- Robust Adversarial Reinforcement Learning
- Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
- Neural Architecture Optimization with Graph VAE
- Self-Evidencing Through Hierarchical Gradient Decomposition: A Dissipative System That Maintains Non-Equilibrium Steady-State by Minimizing Variational Free Energy
- FOX-NAS: Fast, On-device and Explainable Neural Architecture Search
- Effective Model Compression via Stage-wise Pruning
- ELASTIC: Improving CNNs with Dynamic Scaling Policies
- Exploration by Random Network Distillation
- Spiking Neural Network Architecture Search: A Survey
- Hyper-Parameter Optimization: A Review of Algorithms and Applications
- AutoSpeech: Neural Architecture Search for Speaker Recognition
- Automated machine learning: Review of the state-of-the-art and opportunities for healthcare
- Piecewise Linear Units Improve Deep Neural Networks
- Deep Neural Networks for Choice Analysis: Architectural Design with Alternative-Specific Utility Functions
- SGM: A Statistical Godel Machine for Risk-Controlled Recursive Self-Modification
- Stronger NAS with Weaker Predictors
- Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
- Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians
- Multi-Pass Transformer for Machine Translation
- SGAS: Sequential Greedy Architecture Search
- Trustless parallel local search for effective distributed algorithm discovery
- Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation
- Automated Neural Architecture Design for Industrial Defect Detection
- ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures
- PolyKAN: A Polyhedral Analysis Framework for Provable and Approximately Optimal KAN Compression
- Searching Meta Reasoning Skeleton to Guide LLM Reasoning
- On The Statistical Limits of Self-Improving Agents
- Reinforcement Learning in R
- Synthetic Sample Selection via Reinforcement Learning
- Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
- AutoMaAS: Self-Evolving Multi-Agent Architecture Search for Large Language Models
- Generalized Reinforcement Meta Learning for Few-Shot Optimization
- TEA-DNN: the Quest for Time-Energy-Accuracy Co-optimized Deep Neural Networks
- CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search
- From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks
- A Closer Look at Accuracy vs. Robustness
- Computation Reallocation for Object Detection
- CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks
- DMCP: Differentiable Markov Channel Pruning for Neural Networks
- Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
- RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks
- HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
- Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset
- ExMolRL: Phenotype-Target Joint Generation of De Novo Molecules via Multi-Objective Reinforcement Learning
- LV-BERT: Exploiting Layer Variety for BERT
- Auto-Meta: Automated Gradient Based Meta Learner Search
- Accelerating Deep Neural Networks with Spatial Bottleneck Modules
- RAM-NAS: Resource-aware Multiobjective Neural Architecture Search Method for Robot Vision Tasks
- Adversarial AutoAugment
- FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
- DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
- Capacity allocation analysis of neural networks: A tool for principled architecture design
- On the potential for open-endedness in neural networks
- AutoGrow: Automatic Layer Growing in Deep Convolutional Networks
- Network Decoupling: From Regular to Depthwise Separable Convolutions
- Recurrent Additive Networks
- Data-Driven Sparse Structure Selection for Deep Neural Networks
- Joint Search of Data Augmentation Policies and Network Architectures
- Hierarchical Neural Architecture Search for Deep Stereo Matching
- AIPerf: Automated machine learning as an AI-HPC benchmark
- VINNAS: Variational Inference-based Neural Network Architecture Search
- Representation Sharing for Fast Object Detector Search and Beyond
- Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks
- Learning to Prune Filters in Convolutional Neural Networks
- Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion
- DetNAS: Backbone Search for Object Detection
- Not All Ops Are Created Equal!
- Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition
- WAS-VTON: Warping Architecture Search for Virtual Try-on Network
- Analyzing Neural Networks Based on Random Graphs
- DSRNA: Differentiable Search of Robust Neural Architectures
- Fast Neural Architecture Construction using EnvelopeNets
- Shared-Weights Extender and Gradient Voting for Neural Network Expansion
- Learnable Parameter Similarity
- Searching for Accurate Binary Neural Architectures
- Learning Dynamic Routing for Semantic Segmentation
- Conditional Policy Generator for Dynamic Constraint Satisfaction and Optimization
- Single Path One-Shot Neural Architecture Search with Uniform Sampling
- MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training
- Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey
- Recent advances on federated learning: A systematic survey
- Stochastic Bilevel Optimization with Heavy-Tailed Noise
- A Domain Knowledge Informed Approach for Anomaly Detection of Electric Vehicle Interior Sounds
- MoViNets: Mobile Video Networks for Efficient Video Recognition
- Embodied intelligence via learning and evolution
- Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
- Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach
- BraidNet: procedural generation of neural networks for image classification problems using braid theory
- AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models
- On Neural Architecture Search for Resource-Constrained Hardware Platforms
- Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflows
- GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
- From Federated Learning to Federated Neural Architecture Search: A Survey
- Deep Learning for Generic Object Detection: A Survey
- A Semi-Supervised Assessor of Neural Architectures
- Deep learning in multiple animal tracking: A survey
- Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm
- CEM-RL: Combining evolutionary and gradient-based methods for policy search
- Out of Distribution Generalization in Machine Learning
- FLASH: Fast Neural Architecture Search with Hardware Optimization
- RepVGG: Making VGG-style ConvNets Great Again
- Learning to Teach with Dynamic Loss Functions
- Intra-Ensemble in Neural Networks
- OptiProxy-NAS: Optimization Proxy based End-to-End Neural Architecture Search
- Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations
- Learned Optimizers that Scale and Generalize
- Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
- Neural Architecture Search via Bregman Iterations
- Tune: A Research Platform for Distributed Model Selection and Training
- Neural Graph Evolution: Towards Efficient Automatic Robot Design
- Transfer Learning in Deep Reinforcement Learning: A Survey
- A Continuous Encoding-Based Representation for Efficient Multi-Fidelity Multi-Objective Neural Architecture Search
- Paraphrasing Complex Network: Network Compression via Factor Transfer
- A Tensorized Transformer for Language Modeling
- A Survey on Neural Speech Synthesis
- RLCard: A Toolkit for Reinforcement Learning in Card Games
- OnlineAugment: Online Data Augmentation with Less Domain Knowledge
- You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
- NoScope: Optimizing Neural Network Queries over Video at Scale
- Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
- Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
- Exploring Randomly Wired Neural Networks for Image Recognition
- Core-set Sampling for Efficient Neural Architecture Search
- Rapid Model Architecture Adaption for Meta-Learning
- APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
- The AI gambit: leveraging artificial intelligence to combat climate change—opportunities, challenges, and recommendations
- Systematic evaluation of convolution neural network advances on the Imagenet
- HHNAS-AM: Hierarchical Hybrid Neural Architecture Search using Adaptive Mutation Policies
- Cross-Layer Design of Vector-Symbolic Computing: Bridging Cognition and Brain-Inspired Hardware Acceleration
- Differentiable Sparsification for Deep Neural Networks
- Stabilizing Differentiable Architecture Search via Perturbation-based Regularization
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
- Evolutionary-Neural Hybrid Agents for Architecture Search
- Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvature
- Language Models with Transformers
- BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
- CrypTen: Secure Multi-Party Computation Meets Machine Learning
- SOTERIA: In Search of Efficient Neural Networks for Private Inference
- Hyp-RL : Hyperparameter Optimization by Reinforcement Learning
- Hierarchical Representations for Efficient Architecture Search
- MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
- NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- A Comprehensive Survey of Multilingual Neural Machine Translation
- Towards More Practical Adversarial Attacks on Graph Neural Networks
- Practical Block-wise Neural Network Architecture Generation
- Grow-Push-Prune: aligning deep discriminants for effective structural network compression
- Understanding Neural Architecture Search Techniques
- Pareto-NRPA: A Novel Monte-Carlo Search Algorithm for Multi-Objective Optimization
- Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer
- Edge-featured Graph Neural Architecture Search
- An Embedded Deep Learning based Word Prediction
- Multi-Armed Bandits-Based Optimization of Decision Trees
- Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization
- Regularized Evolutionary Population-Based Training
- MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
- SO-PIFRNN: Self-optimization physics-informed Fourier-features randomized neural network for solving partial differential equations
- Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
- Empowering Time Series Forecasting with LLM-Agents
- RLGS: Reinforcement Learning-Based Adaptive Hyperparameter Tuning for Gaussian Splatting
- Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization
- Learned Low Precision Graph Neural Networks
- A Generative Model for Sampling High-Performance and Diverse Weights for\n Neural Networks
- Fast Neural Network Adaptation via Parameter Remapping and Architecture Search
- FedCD: A Fairness-aware Federated Cognitive Diagnosis Framework
- Efficient Automatic Meta Optimization Search for Few-Shot Learning
- Large-Scale Evolution of Image Classifiers
- HyperSTAR: Task-Aware Hyperparameters for Deep Networks
- AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates
- Intriguing Properties of Adversarial Examples
- Graph Lineages and Skeletal Graph Products
- BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels
- Blending Diverse Physical Priors with Neural Networks
- Data Aware Differentiable Neural Architecture Search for Tiny Keyword Spotting Applications
- PhaseNAS: Language-Model Driven Architecture Search with Dynamic Phase Adaptation
- Beyond Model Base Selection: Weaving Knowledge to Master Fine-grained Neural Network Design
- Sampled Training and Node Inheritance for Fast Evolutionary Neural Architecture Search
- Theory-Inspired Path-Regularized Differential Network Architecture Search
- ASNN: Learning to Suggest Neural Architectures from Performance Distributions
- Machine Learning With Neuromorphic Photonics
- A Reinforcement Learning Approach for Sequential Spatial Transformer\n Networks
- Explore-Exploit: A Framework for Interactive and Online Learning
- A Roadmap for Robust End-to-End Alignment
- Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
- The Price equation reveals a universal force-metric-bias law of algorithmic learning and natural selection
- Transfer Learning to Learn with Multitask Neural Model Search
- Self-Supervised Neural Architecture Search for Imbalanced Datasets
- IRLAS: Inverse Reinforcement Learning for Architecture Search
- Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification
- Refining the Structure of Neural Networks Using Matrix Conditioning
- DIVA: Dataset Derivative of a Learning Task
- Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search
- Machine Learning Systems for Intelligent Services in the IoT: A Survey
- Techniques for Automated Machine Learning
- Learning Intrinsic Sparse Structures within Long Short-Term Memory
- AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
- Challenges for cognitive decoding using deep learning methods
- Towards Execution-Grounded Automated AI Research
- Design and Implementation of an Annotation-Driven Drone Autonomy Tool Using YOLOv8–V11 Architectures for Real-Time Object Detection and Distance Estimation
- Counterfactuals uncover the modular structure of deep generative models
- AI Matrix - Synthetic Benchmarks for DNN
- MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning
- Memory-efficient Embedding for Recommendations
- Incorporating domain knowledge into neural-guided search
- EPNAS: Efficient Progressive Neural Architecture Search
- Reducing Inference Latency with Concurrent Architectures for Image Recognition
- Knowledge accumulating: The general pattern of learning
- ADWPNAS: Architecture-Driven Weight Prediction for Neural Architecture Search
- Gradient-free Policy Architecture Search and Adaptation
- Neural Architecture Search for Gliomas Segmentation on Multimodal Magnetic Resonance Imaging
- Towards Binary-Valued Gates for Robust LSTM Training
- confopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methods
- MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
- TimeGate: Conditional Gating of Segments in Long-range Activities
- Enhanced Gradient for Differentiable Architecture Search
- Multi-Scale Spatially-Asymmetric Recalibration for Image Classification
- Latent Domain Learning with Dynamic Residual Adapters
- Quantum Architecture Search via Deep Reinforcement Learning
- MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
- BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search
- Integrating Multiple Receptive Fields through Grouped Active Convolution
- Mixed Variable Bayesian Optimization with Frequency Modulated Kernels
- Nonparametric Neural Networks
- Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
- MobileDepth: Efficient Monocular Depth Prediction on Mobile Devices
- RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
- Generating Neural Networks with Neural Networks
- StyleNAS: An Empirical Study of Neural Architecture Search to Uncover Surprisingly Fast End-to-End Universal Style Transfer Networks
- Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling
- Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR
- Rotational Unit of Memory
- Teachers Do More Than Teach: Compressing Image-to-Image Models
- Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
- Effects of relational graph modularity and depth on the learning performance of neural networks
- Balanced One-shot Neural Architecture Optimization
- UniformAugment: A Search-free Probabilistic Data Augmentation Approach
- DC-NAS: Divide-and-Conquer Neural Architecture Search
- Zero-Shot Neural Architecture Search with Weighted Response Correlation
- Efficient Federated Learning with Timely Update Dissemination
- Evaluation of Large Language Model-Driven AutoML in Data and Model Management from Human-Centered Perspective
- Neural Program Synthesis with Priority Queue Training
- Cyclic Differentiable Architecture Search
- CIFAR-10 [wikipedia]
- Neural architecture search [wikipedia]
- Neural network (machine learning) [wikipedia]
- Quoc V. Le [wikipedia]
Discussions
Related