Neural Architecture Search with Reinforcement Learning

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.

References in corpus (18)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Striving for Simplicity: The All Convolutional Net
• Recurrent Neural Network Regularization
• Densely Connected Convolutional Networks
• Wide Residual Networks
• Theoretical Models of Learning to Learn
• Sequence Level Training with Recurrent Neural Networks
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• FractalNet: Ultra-Deep Neural Networks without Residuals
• Pointer Sentinel Mixture Models
• Learning to learn by gradient descent by gradient descent
• Deep Networks with Stochastic Depth
• How to Construct Deep Recurrent Neural Networks
• Identity Mappings in Deep Residual Networks
• Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
• Learning to Optimize
• Learning to Compose Neural Networks for Question Answering
• Neural Programmer: Inducing Latent Programs with Gradient Descent

Cited by in corpus (1098)

• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• A Brief Survey of Deep Reinforcement Learning
• DeepXDE: A deep learning library for solving differential equations
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• Neural Architecture Search: A Survey
• AutoML: A Survey of the State-of-the-Art
• Pre-trained Models for Natural Language Processing: A Survey
• Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
• fPINNs: Fractional Physics-Informed Neural Networks
• Recent advances and clinical applications of deep learning in medical image analysis
• Deep Face Recognition: A Survey
• Automatically designing CNN architectures using genetic algorithm for image classification
• A Survey of Model Compression and Acceleration for Deep Neural Networks
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Searching for Activation Functions
• AutoAugment: Learning Augmentation Policies from Data
• A Survey on Evolutionary Neural Architecture Search
• Tune: A Research Platform for Distributed Model Selection and Training
• Regularized Deep Networks in Intelligent Transportation Systems: A Taxonomy and a Case Study
• Impact of Fully Connected Layers on Performance of Convolutional Neural Networks for Image Classification
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better
• Object Detection in 20 Years: A Survey
• Deep Reinforcement Learning: An Overview
• Large-Scale Evolution of Image Classifiers
• Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
• Data Augmentation using Random Image Cropping and Patching for Deep CNNs
• Regularizing and Optimizing LSTM Language Models
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
• Multi-Task Learning with Deep Neural Networks: A Survey
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Robust Adversarial Reinforcement Learning
• Learning to reinforcement learn
• Embodied Intelligence via Learning and Evolution
• MixConv: Mixed Depthwise Convolutional Kernels
• Systematic evaluation of CNN advances on the ImageNet
• Compute Trends Across Three Eras of Machine Learning
• Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
• ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
• SNAS: Stochastic Neural Architecture Search
• Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools
• NAS-FAS: Static-Dynamic Central Difference Network Search for Face Anti-Spoofing
• MCUNet: Tiny Deep Learning on IoT Devices
• A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects
• Neural Architecture Search with Bayesian Optimisation and Optimal Transport
• Understanding and Robustifying Differentiable Architecture Search
• DARTS+: Improved Differentiable Architecture Search with Early Stopping
• Machine Learning for Microcontroller-Class Hardware: A Review
• Exploration by Random Network Distillation
• Random Search and Reproducibility for Neural Architecture Search
• ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
• Single Path One-Shot Neural Architecture Search with Uniform Sampling
• Deep Learning for Generic Object Detection: A Survey
• Hierarchical Neural Architecture Search for Deep Stereo Matching
• Hierarchical Representations for Efficient Architecture Search
• HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
• One-Shot Neural Architecture Search via Self-Evaluated Template Network
• Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis
• Neural Optimizer Search with Reinforcement Learning
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• Reinforced Continual Learning
• Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
• Simple And Efficient Architecture Search for Convolutional Neural Networks
• A Survey on Neural Speech Synthesis
• Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges
• Neural Architecture Transfer
• Tiny Machine Learning: Progress and Futures
• DetNAS: Backbone Search for Object Detection
• Efficient spectrum prediction and inverse design for plasmonic waveguide systems based on artificial neural networks
• Bringing AI To Edge: From Deep Learning's Perspective
• NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size
• TSM: Temporal Shift Module for Efficient Video Understanding
• Progressive Neural Architecture Search
• Evaluating the Search Phase of Neural Architecture Search
• Differentiable Quantum Architecture Search
• Mobile Augmented Reality: User Interfaces, Frameworks, and Intelligence
• DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
• Automated Machine Learning: State-of-The-Art and Open Challenges
• Transfer Learning in Deep Reinforcement Learning: A Survey
• Path-Level Network Transformation for Efficient Architecture Search
• MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
• AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
• Automatic Sleep Staging of EEG Signals: Recent Development, Challenges, and Future Directions
• AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
• DeepArchitect: Automatically Designing and Training Deep Architectures
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• Network Pruning via Transformable Architecture Search
• Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition
• A Practical Survey on Faster and Lighter Transformers
• Optimization for deep learning: theory and algorithms
• An Analysis of Neural Language Modeling at Multiple Scales
• The Modern Mathematics of Deep Learning
• AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
• Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
• Learning Intrinsic Sparse Structures within Long Short-Term Memory
• Path-Restore: Learning Network Path Selection for Image Restoration
• N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning
• Graph HyperNetworks for Neural Architecture Search
• FasterSeg: Searching for Faster Real-time Semantic Segmentation
• Learning to Reason: End-to-End Module Networks for Visual Question Answering
• AdaNet: Adaptive Structural Learning of Artificial Neural Networks
• Causal Discovery with Reinforcement Learning
• Learned Optimizers that Scale and Generalize
• Review: Deep Learning in Electron Microscopy
• Automated Machine Learning in Practice: State of the Art and Recent Results
• Dataset Condensation with Gradient Matching
• Stochastic analysis of heterogeneous porous material with modified neural architecture search (NAS) based physics-informed neural networks using transfer learning
• BRP-NAS: Prediction-based NAS using GCNs
• Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing
• Once-for-All: Train One Network and Specialize it for Efficient Deployment
• Differentiable Augmentation for Data-Efficient GAN Training
• MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
• Smooth Adversarial Training
• PP-LCNet: A Lightweight CPU Convolutional Neural Network
• Toward Deep Supervised Anomaly Detection: Reinforcement Learning from Partially Labeled Anomaly Data
• Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search
• Trellis Networks for Sequence Modeling
• CEM-RL: Combining evolutionary and gradient-based methods for policy search
• Recent Progress in the CUHK Dysarthric Speech Recognition System
• Neural Predictor based Quantum Architecture Search
• FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
• Adversarial AutoAugment
• Stealing Neural Networks via Timing Side Channels
• Best Practices for Scientific Research on Neural Architecture Search
• Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search
• Any equation is a forest: Symbolic genetic algorithm for discovering open-form partial differential equations (SGA-PDE)
• D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
• Paraphrasing Complex Network: Network Compression via Factor Transfer
• Meta-Learning Update Rules for Unsupervised Representation Learning
• Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search
• Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
• Peephole: Predicting Network Performance Before Training
• SkyNet: a Hardware-Efficient Method for Object Detection and Tracking on Embedded Systems
• An overview of mixing augmentation methods and augmentation strategies
• SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
• Exploring Randomly Wired Neural Networks for Image Recognition
• Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithm
• Stabilizing Differentiable Architecture Search via Perturbation-based Regularization
• Evolving Deep Convolutional Neural Networks for Image Classification
• NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search
• Heterogeneous Multilayer Generalized Operational Perceptron
• How to train your MAML
• Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling
• A Closer Look at Accuracy vs. Robustness
• Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
• Applications and Techniques for Fast Machine Learning in Science
• Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks
• Network Decoupling: From Regular to Depthwise Separable Convolutions
• Analyzing Human-Human Interactions: A Survey
• River Ice Segmentation with Deep Learning
• Weighted Random Search for CNN Hyperparameter Optimization
• Dynamic Convolution: Attention over Convolution Kernels
• NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithm
• Probabilistic Neural Architecture Search
• GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
• Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
• Automated Machine Learning on Graphs: A Survey
• Learning to Continually Learn
• A newcomer's guide to deep learning for inverse design in nano-photonics
• Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
• BNAS:An Efficient Neural Architecture Search Approach Using Broad Scalable Architecture
• Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students
• Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
• DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
• Hypernetwork functional image representation
• Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
• Discrete Sequential Prediction of Continuous Actions for Deep RL
• ASAP: Architecture Search, Anneal and Prune
• FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
• Auto-GNN: Neural Architecture Search of Graph Neural Networks
• Breaking the Softmax Bottleneck: A High-Rank RNN Language Model
• CrypTen: Secure Multi-Party Computation Meets Machine Learning
• SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties
• Discovering Neural Wirings
• A Genetic Programming Approach to Designing Convolutional Neural Network Architectures
• Dynamic Evaluation of Neural Sequence Models
• Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement
• MaskConnect: Connectivity Learning by Gradient Descent
• On Neural Architecture Search for Resource-Constrained Hardware Platforms
• Universal Activation Function For Machine Learning
• AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning
• SEMI-FND: Stacked Ensemble Based Multimodal Inference For Faster Fake News Detection
• Effective and Efficient Dropout for Deep Convolutional Neural Networks
• ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction
• Evolving Normalization-Activation Layers
• AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search
• Predicting atmospheric optical properties for radiative transfer computations using neural networks
• Cross-dimensional transfer learning in medical image segmentation with deep learning
• Forward and Reverse Gradient-Based Hyperparameter Optimization
• Image quality assessment for machine learning tasks using meta-reinforcement learning
• Out of Distribution Generalization in Machine Learning
• Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective
• Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers
• NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
• The importance of better models in stochastic optimization
• Towards Green Automated Machine Learning: Status Quo and Future Directions
• Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework
• LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
• HAQ: Hardware-Aware Automated Quantization with Mixed Precision
• Learning Generalisable Omni-Scale Representations for Person Re-Identification
• On the State of the Art of Evaluation in Neural Language Models
• Auto-Ensemble: An Adaptive Learning Rate Scheduling based Deep Learning Model Ensembling
• MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
• Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
• Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
• BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction
• Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge
• Drawing Early-Bird Tickets: Towards More Efficient Training of Deep Networks
• EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search
• Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets
• A Hybrid Convolutional Variational Autoencoder for Text Generation
• Hybrid Tensor Decomposition in Neural Network Compression
• Quantum Embedding Search for Quantum Machine Learning
• A neural network walks into a lab: towards using deep nets as models for human behavior
• NoScope: Optimizing Neural Network Queries over Video at Scale
• RepVGG: Making VGG-style ConvNets Great Again
• Language Models with Transformers
• Semi-Supervised Neural Architecture Search
• AutoGAN: Neural Architecture Search for Generative Adversarial Networks
• Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly
• Reinforcement Learning Applications
• DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search
• Scalable Deep Learning on Distributed Infrastructures: Challenges, Techniques and Tools
• Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters
• Four Things Everyone Should Know to Improve Batch Normalization
• Revisiting Activation Regularization for Language RNNs
• Detecting solar system objects with convolutional neural networks
• ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
• Neural Architecture Search without Training
• A Comprehensive Review of Modern Object Segmentation Approaches
• Fast-Slow Recurrent Neural Networks
• DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programs
• Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identification
• Neural Architecture Search For Keyword Spotting
• MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
• Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices
• Dynamic Neural Networks: A Survey
• Progressive Skeletonization: Trimming more fat from a network at initialization
• Towards Binary-Valued Gates for Robust LSTM Training
• You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization
• Simple, Distributed, and Accelerated Probabilistic Programming
• NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks
• AGAN: Towards Automated Design of Generative Adversarial Networks
• BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models
• Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
• Temporal Convolutional Attention-based Network For Sequence Modeling
• Deep Learning Based Chatbot Models
• UniformAugment: A Search-free Probabilistic Data Augmentation Approach
• Searching Central Difference Convolutional Networks for Face Anti-Spoofing
• Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search
• Universality and individuality in neural dynamics across large populations of recurrent networks
• Quantum Architecture Search via Deep Reinforcement Learning
• Adversarially Robust Neural Architectures
• ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding
• RMM: Reinforced Memory Management for Class-Incremental Learning
• Learning Deep Morphological Networks with Neural Architecture Search
• On-device Training: A First Overview on Existing Systems
• Contrastive Self-supervised Neural Architecture Search
• PHOTONAI -- A Python API for Rapid Machine Learning Model Development
• SPGNet: Semantic Prediction Guidance for Scene Parsing
• AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates
• Hyp-RL : Hyperparameter Optimization by Reinforcement Learning
• Deep Independently Recurrent Neural Network (IndRNN)
• Deeper Insights into Weight Sharing in Neural Architecture Search
• MaxUp: A Simple Way to Improve Generalization of Neural Network Training
• PSLT: A Light-weight Vision Transformer with Ladder Self-Attention and Progressive Shift
• Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future
• Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
• Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
• Blending Diverse Physical Priors with Neural Networks
• StressNAS: Affect State and Stress Detection Using Neural Architecture Search
• Finding Competitive Network Architectures Within a Day Using UCT
• Reinforced Evolutionary Neural Architecture Search
• Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
• Sample-Efficient Neural Architecture Search by Learning Action Space
• CryptoNAS: Private Inference on a ReLU Budget
• Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
• Evaluating Efficient Performance Estimators of Neural Architectures
• RLCard: A Toolkit for Reinforcement Learning in Card Games
• Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search
• Computation Reallocation for Object Detection
• Budgeted Training: Rethinking Deep Neural Network Training Under Resource Constraints
• GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
• Tensor Decomposition for Model Reduction in Neural Networks: A Review
• On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition
• AutoLoss: Learning Discrete Schedules for Alternate Optimization
• FreeREA: Training-Free Evolution-based Architecture Search
• Data-Driven Sparse Structure Selection for Deep Neural Networks
• Improving Auto-Augment via Augmentation-Wise Weight Sharing
• FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
• Recurrent Additive Networks
• Understanding Neural Architecture Search Techniques
• FFV-PINN: A Fast Physics-Informed Neural Network with Simplified Finite Volume Discretization and Residual Correction
• Counterfactuals uncover the modular structure of deep generative models
• EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer
• Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
• Approximate Bayesian Uncertainties on Deep Learning Dynamical Mass Estimates of Galaxy Clusters
• Constrained Design of Deep Iris Networks
• On Feature Normalization and Data Augmentation
• Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling
• Learning to Prune Filters in Convolutional Neural Networks
• Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back
• Triple-level Model Inferred Collaborative Network Architecture for Video Deraining
• One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
• Latency-Aware Differentiable Neural Architecture Search
• Pareto-Optimal Quantized ResNet Is Mostly 4-bit
• Neural Program Synthesis with Priority Queue Training
• AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
• Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Too Much Accuracy
• Sub-Architecture Ensemble Pruning in Neural Architecture Search
• Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
• DSNAS: Direct Neural Architecture Search without Parameter Retraining
• Trust-Region Method with Deep Reinforcement Learning in Analog Design Space Exploration
• FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
• Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrieval
• Connectivity Learning in Multi-Branch Networks
• Theory-Inspired Path-Regularized Differential Network Architecture Search
• RC-DARTS: Resource Constrained Differentiable Architecture Search
• Auto-Meta: Automated Gradient Based Meta Learner Search
• A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
• CARS: Continuous Evolution for Efficient Neural Architecture Search
• AutoHAS: Efficient Hyperparameter and Architecture Search
• VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing
• DropNAS: Grouped Operation Dropout for Differentiable Architecture Search
• Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices
• AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search
• How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS
• PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search
• TF-Coder: Program Synthesis for Tensor Manipulations
• Meta-Learning Symmetries by Reparameterization
• Intriguing Properties of Adversarial Examples
• A Comprehensive Survey of Multilingual Neural Machine Translation
• NAS-FCOS: Fast Neural Architecture Search for Object Detection
• StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking
• Deep Long Audio Inpainting
• Diverse Branch Block: Building a Convolution as an Inception-like Unit
• Federated Neural Architecture Search
• APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
• EfficientTDNN: Efficient Architecture Search for Speaker Recognition
• The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization
• Automatically Evolving CNN Architectures Based on Blocks
• FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining
• Neural Language Modeling by Jointly Learning Syntax and Lexicon
• XNAS: Neural Architecture Search with Expert Advice
• Deriving Neural Architectures from Sequence and Graph Kernels
• Meta-Learning through Hebbian Plasticity in Random Networks
• DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation
• Kernel-based Graph Learning from Smooth Signals: A Functional Viewpoint
• Probabilistic Dual Network Architecture Search on Graphs
• Practical Block-wise Neural Network Architecture Generation
• BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables
• SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
• AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations
• Accelerate CNNs from Three Dimensions: A Comprehensive Pruning Framework
• Not All Ops Are Created Equal!
• Resource-Efficient Neural Networks for Embedded Systems
• When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks
• Bayesian Learning of Sum-Product Networks
• PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
• Joint Neural Architecture Search and Quantization
• Evolving Reinforcement Learning Algorithms
• Discovering General-Purpose Active Learning Strategies
• Evolving Robust Neural Architectures to Defend from Adversarial Attacks
• Reinforcement Learning Driven Heuristic Optimization
• Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
• Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustness
• Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection
• MANAS: Multi-Agent Neural Architecture Search
• Interoceptive robustness through environment-mediated morphological development
• Memory-efficient Embedding for Recommendations
• DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures
• HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning
• Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions
• Few-Shot Speaker Identification Using Lightweight Prototypical Network with Feature Grouping and Interaction
• BlockQNN: Efficient Block-wise Neural Network Architecture Generation
• C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation
• Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
• Towards AutoML in the presence of Drift: first results
• MultiScene: A Large-scale Dataset and Benchmark for Multi-scene Recognition in Single Aerial Images
• Evolutionary Neural Architecture Search for Retinal Vessel Segmentation
• AdaBits: Neural Network Quantization with Adaptive Bit-Widths
• Neural Architecture Generator Optimization
• ReNAS:Relativistic Evaluation of Neural Architecture Search
• Question Answering from Unstructured Text by Retrieval and Comprehension
• HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
• Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels
• LPYOLO: Low Precision YOLO for Face Detection on FPGA
• Neural Feature Search for RGB-Infrared Person Re-Identification
• MoViNets: Mobile Video Networks for Efficient Video Recognition
• Learned Low Precision Graph Neural Networks
• How Powerful are Performance Predictors in Neural Architecture Search?
• Automated Concatenation of Embeddings for Structured Prediction
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition
• Chameleon: Adaptive Code Optimization for Expedited Deep Neural Network Compilation
• Graph-Based Global Reasoning Networks
• Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
• Automatic Mixed-Precision Quantization Search of BERT
• Knowledge distillation via adaptive instance normalization
• Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
• Meta-learning curiosity algorithms
• Recent Advances in Neural Program Synthesis
• Hardware-Centric AutoML for Mixed-Precision Quantization
• Real-time Federated Evolutionary Neural Architecture Search
• Evolutionary Neural Architecture Search Supporting Approximate Multipliers
• Exploring Benefits of Transfer Learning in Neural Machine Translation
• Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
• DMCP: Differentiable Markov Channel Pruning for Neural Networks
• MixPath: A Unified Approach for One-shot Neural Architecture Search
• One-Shot Neural Architecture Search via Compressive Sensing
• Multigrid Predictive Filter Flow for Unsupervised Learning on Videos
• Hardware/Software Co-Exploration of Neural Architectures
• Manas: Mining Software Repositories to Assist AutoML
• Large Scale Evolution of Convolutional Neural Networks Using Volunteer Computing
• Rafiki: Machine Learning as an Analytics Service System
• MoBiNet: A Mobile Binary Network for Image Classification
• Evolutionary-Neural Hybrid Agents for Architecture Search
• Parallel Architecture and Hyperparameter Search via Successive Halving and Classification
• Multinomial Distribution Learning for Effective Neural Architecture Search
• Goal-directed graph construction using reinforcement learning
• Funnel Activation for Visual Recognition
• Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
• Exploring Shared Structures and Hierarchies for Multiple NLP Tasks
• Using Small Proxy Datasets to Accelerate Hyperparameter Search
• EffNet: An Efficient Structure for Convolutional Neural Networks
• AutoSpeech: Neural Architecture Search for Speaker Recognition
• AutoPose: Searching Multi-Scale Branch Aggregation for Pose Estimation
• PILAE: A Non-gradient Descent Learning Scheme for Deep Feedforward Neural Networks
• Evolutionary Architecture Search for Graph Neural Networks
• DASS: Differentiable Architecture Search for Sparse neural networks
• Learning to Optimize in Swarms
• Efficient Differentiable Neural Architecture Search with Meta Kernels
• Searching for Winograd-aware Quantized Networks
• Convolution Neural Network Architecture Learning for Remote Sensing Scene Classification
• Constructing Deep Neural Networks by Bayesian Network Structure Learning
• Towards NNGP-guided Neural Architecture Search
• GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning
• Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
• Using a thousand optimization tasks to learn hyperparameter search strategies
• ExplainaBoard: An Explainable Leaderboard for NLP
• Towards More Practical Adversarial Attacks on Graph Neural Networks
• Learnable Embedding Space for Efficient Neural Architecture Compression
• To Share or Not To Share: A Comprehensive Appraisal of Weight-Sharing
• Observation Space Matters: Benchmark and Optimization Algorithm
• FPGA/DNN Co-Design: An Efficient Design Methodology for IoT Intelligence on the Edge
• Speedy Performance Estimation for Neural Architecture Search
• AdversarialNAS: Adversarial Neural Architecture Search for GANs
• Fine-Grained Neural Architecture Search
• Densely Connected Search Space for More Flexible Neural Architecture Search
• Reinforcement Learning and Adaptive Sampling for Optimized DNN Compilation
• Stronger NAS with Weaker Predictors
• BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget
• Hyperparameter Optimization via Sequential Uniform Designs
• AM-LFS: AutoML for Loss Function Search
• Learning Dynamic Routing for Semantic Segmentation
• Efficient Bitwidth Search for Practical Mixed Precision Neural Network
• SalNAS: Efficient Saliency-prediction Neural Architecture Search with self-knowledge distillation
• Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot
• A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery
• Balanced Symmetric Cross Entropy for Large Scale Imbalanced and Noisy Data
• Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
• Multiresolution Convolutional Autoencoders
• Neural Network Architecture Search Enabled Wide-Deep Learning (NAS-WD) for Spatially Heterogenous Property Awared Chicken Woody Breast Classification and Hardness Regression
• Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
• V-NAS: Neural Architecture Search for Volumetric Medical Image Segmentation
• AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
• LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
• Pose Neural Fabrics Search
• BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search
• Analyzing and Mitigating Interference in Neural Architecture Search
• SGAS: Sequential Greedy Architecture Search
• Dynamic Optimization of Neural Network Structures Using Probabilistic Modeling
• FBNetV5: Neural Architecture Search for Multiple Tasks in One Run
• DHP: Differentiable Meta Pruning via HyperNetworks
• Learning To Simulate
• Gradient-free Policy Architecture Search and Adaptation
• PAMS: Quantized Super-Resolution via Parameterized Max Scale
• DVOLVER: Efficient Pareto-Optimal Neural Network Architecture Search
• Bayesian Learning of Neural Network Architectures
• A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search
• Neuroevolution of Neural Network Architectures Using CoDeepNEAT and Keras
• Core-set Sampling for Efficient Neural Architecture Search
• You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
• SapientML: Synthesizing Machine Learning Pipelines by Learning from Human-Written Solutions
• The Low-Rank Simplicity Bias in Deep Networks
• A Semi-Supervised Assessor of Neural Architectures
• GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet
• Training-Time-Friendly Network for Real-Time Object Detection
• Feature Partitioning for Efficient Multi-Task Architectures
• Parity Models: A General Framework for Coding-Based Resilience in ML Inference
• Designing deep neural networks for driver intention recognition
• Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search
• Efficient Deep Neural Networks
• Generating Neural Networks with Neural Networks
• Differentiable architecture search with multi-dimensional attention for spiking neural networks
• Graph-attention-based Casual Discovery with Trust Region-navigated Clipping Policy Optimization
• AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture Search
• Sampled Training and Node Inheritance for Fast Evolutionary Neural Architecture Search
• A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction
• User Response Prediction in Online Advertising
• Neural Architecture Search for Class-incremental Learning
• From Federated Learning to Federated Neural Architecture Search: A Survey
• Cyclic Differentiable Architecture Search
• Deep Multimodal Neural Architecture Search
• Map-based Multi-Policy Reinforcement Learning: Enhancing Adaptability of Robots by Deep Reinforcement Learning
• Autonomous Deep Learning: A Genetic DCNN Designer for Image Classification
• Efficient Neural Architecture Search via Proximal Iterations
• Meta-Learning for Contextual Bandit Exploration
• A Memory-Efficient Dynamic Image Reconstruction Method using Neural Fields
• Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search
• Techniques for Automated Machine Learning
• TAPAS: Train-less Accuracy Predictor for Architecture Search
• Searching to Exploit Memorization Effect in Learning from Corrupted Labels
• Automatic Model Selection for Neural Networks
• Towards Similarity Graphs Constructed by Deep Reinforcement Learning
• NAS-VAD: Neural Architecture Search for Voice Activity Detection
• Deep Networks from the Principle of Rate Reduction
• Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians
• SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials
• MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
• An Introduction to Neural Architecture Search for Convolutional Networks
• DSRNA: Differentiable Search of Robust Neural Architectures
• AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks
• AutoCaption: Image Captioning with Neural Architecture Search
• ProBO: Versatile Bayesian Optimization Using Any Probabilistic Programming Language
• Improving One-shot NAS by Suppressing the Posterior Fading
• Online Hyper-parameter Learning for Auto-Augmentation Strategy
• Improving Neural Architecture Search Image Classifiers via Ensemble Learning
• ReinBo: Machine Learning pipeline search and configuration with Bayesian Optimization embedded Reinforcement Learning
• Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
• Optimization Algorithm Inspired Deep Neural Network Structure Design
• DartsReNet: Exploring new RNN cells in ReNet architectures
• Growing Efficient Deep Networks by Structured Continuous Sparsification
• MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
• SQuantizer: Simultaneous Learning for Both Sparse and Low-precision Neural Networks
• A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics
• Hierarchical Neural Architecture Search via Operator Clustering
• Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations
• Balanced One-shot Neural Architecture Optimization
• Neural Architecture Optimization with Graph VAE
• Nonparametric Neural Networks
• NAS-Navigator: Visual Steering for Explainable One-Shot Deep Neural Network Synthesis
• NASI: Label- and Data-agnostic Neural Architecture Search at Initialization
• Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization
• Deep RGB-D Saliency Detection with Depth-Sensitive Attention and Automatic Multi-Modal Fusion
• Energy-Aware Neural Architecture Optimization with Fast Splitting Steepest Descent
• A Novel Framework for Neural Architecture Search in the Hill Climbing Domain
• DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture
• CATE: Computation-aware Neural Architecture Encoding with Transformers
• Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search
• Wise-SrNet: A Novel Architecture for Enhancing Image Classification by Learning Spatial Resolution of Feature Maps
• Flexible Multi-task Networks by Learning Parameter Allocation
• Prune and Replace NAS
• Sharpness-aware Quantization for Deep Neural Networks
• Branched Multi-Task Networks: Deciding What Layers To Share
• Efficient Attention Network: Accelerate Attention by Searching Where to Plug
• Data-driven Neural Architecture Learning For Financial Time-series Forecasting
• Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization
• Leveraging End-to-End Speech Recognition with Neural Architecture Search
• AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
• Learning Versatile Convolution Filters for Efficient Visual Recognition
• Breaking the Activation Function Bottleneck through Adaptive Parameterization
• Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs
• Neural Architecture Search For Fault Diagnosis
• Neural Architecture Search using Property Guided Synthesis
• Smallify: Learning Network Size while Training
• IRLAS: Inverse Reinforcement Learning for Architecture Search
• Super Resolution Using Segmentation-Prior Self-Attention Generative Adversarial Network
• Measuring Visual Generalization in Continuous Control from Pixels
• Circumventing Outliers of AutoAugment with Knowledge Distillation
• Multi-objective Asynchronous Successive Halving
• A Batched Scalable Multi-Objective Bayesian Optimization Algorithm
• Accelerating Deep Neural Networks with Spatial Bottleneck Modules
• Backpropagation-Free 4D Continuous Ant-Based Neural Topology Search
• Genetic Deep Learning for Lung Cancer Screening
• Rethinking Graph Neural Architecture Search from Message-passing
• Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
• PV-NAS: Practical Neural Architecture Search for Video Recognition
• Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
• Domain-Aware Dynamic Networks
• Teachers Do More Than Teach: Compressing Image-to-Image Models
• Semantic-Based Neural Network Repair
• Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
• Constrained deep neural network architecture search for IoT devices accounting hardware calibration
• Neural Anisotropy Directions
• Ordering-Based Causal Discovery with Reinforcement Learning
• Fast Neural Architecture Construction using EnvelopeNets
• NAX: Co-Designing Neural Network and Hardware Architecture for Memristive Xbar based Computing Systems
• Deep Learning in Information Security
• Joint Search of Data Augmentation Policies and Network Architectures
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
• Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
• Deep neural network initialization with decision trees
• Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation
• Automatically Searching for U-Net Image Translator Architecture
• ImmuNeCS: Neural Committee Search by an Artificial Immune System
• Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search
• S3NAS: Fast NPU-aware Neural Architecture Search Methodology
• DrNAS: Dirichlet Neural Architecture Search
• Cross-Domain Perceptual Reward Functions
• Progressive Neural Networks for Image Classification
• A Survey On Anti-Spoofing Methods For Face Recognition with RGB Cameras of Generic Consumer Devices
• DIFER: Differentiable Automated Feature Engineering
• Accuracy Prediction with Non-neural Model for Neural Architecture Search
• Learning Differentiable Programs with Admissible Neural Heuristics
• GradSign: Model Performance Inference with Theoretical Insights
• Rethinking the Number of Channels for the Convolutional Neural Network
• TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning
• Learning Strict Identity Mappings in Deep Residual Networks
• AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data
• A Highly Configurable Hardware/Software Stack for DNN Inference Acceleration
• AutoML to Date and Beyond: Challenges and Opportunities
• HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
• Model Complexity of Deep Learning: A Survey
• Learning Test-time Augmentation for Content-based Image Retrieval
• Multi-objective Neural Architecture Search via Non-stationary Policy Gradient
• Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection
• Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR
• VINNAS: Variational Inference-based Neural Network Architecture Search
• AutoGrow: Automatic Layer Growing in Deep Convolutional Networks
• Efficient Decoupled Neural Architecture Search by Structure and Operation Sampling
• RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation
• AOGNets: Compositional Grammatical Architectures for Deep Learning
• On the Privacy Risks of Cell-Based NAS Architectures
• Compiler-Level Matrix Multiplication Optimization for Deep Learning
• POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique
• ROMA: Run-Time Object Detection To Maximize Real-Time Accuracy
• Exploiting Uncertainties from Ensemble Learners to Improve Decision-Making in Healthcare AI
• Neural Architecture Search by Estimation of Network Structure Distributions
• Graph-guided Architecture Search for Real-time Semantic Segmentation
• RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation
• AMEIR: Automatic Behavior Modeling, Interaction Exploration and MLP Investigation in the Recommender System
• InstaNAS: Instance-aware Neural Architecture Search
• HeterPS: Distributed Deep Learning With Reinforcement Learning Based Scheduling in Heterogeneous Environments
• Evolving Search Space for Neural Architecture Search
• Network Transplanting
• K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
• Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices
• How can AI Automate End-to-End Data Science?
• DARC: Differentiable ARchitecture Compression
• Self-Organizing Intelligent Matter: A blueprint for an AI generating algorithm
• Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks
• Controlling Model Complexity in Probabilistic Model-Based Dynamic Optimization of Neural Network Structures
• Discovering Robust Convolutional Architecture at Targeted Capacity: A Multi-Shot Approach
• Exploiting Channel Similarity for Accelerating Deep Convolutional Neural Networks
• Sparsely Aggregated Convolutional Networks
• Deep Neural Architecture Search with Deep Graph Bayesian Optimization
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods
• NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
• Generalization Guarantees for Neural Architecture Search with Train-Validation Split
• Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs
• Catalyst.RL: A Distributed Framework for Reproducible RL Research
• EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search
• DOTS: Decoupling Operation and Topology in Differentiable Architecture Search
• Pay Attention when Required
• Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks
• Towards Oracle Knowledge Distillation with Neural Architecture Search
• RARTS: An Efficient First-Order Relaxed Architecture Search Method
• GENNAPE: Towards Generalized Neural Architecture Performance Estimators
• DeepMapping: Learned Data Mapping for Lossless Compression and Efficient Lookup
• Integrating Large Circular Kernels into CNNs through Neural Architecture Search
• Characterizing Deep Learning Training Workloads on Alibaba-PAI
• GDOD: Effective Gradient Descent using Orthogonal Decomposition for Multi-Task Learning
• Transfer Learning to Learn with Multitask Neural Model Search
• FNAS: Uncertainty-Aware Fast Neural Architecture Search
• A Committee of Convolutional Neural Networks for Image Classication in the Concurrent Presence of Feature and Label Noise
• Synthetic Sample Selection via Reinforcement Learning
• Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization
• AI Matrix - Synthetic Benchmarks for DNN
• SOTERIA: In Search of Efficient Neural Networks for Private Inference
• Learning to Design RNA
• Policy-GNN: Aggregation Optimization for Graph Neural Networks
• Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation
• NAS-Count: Counting-by-Density with Neural Architecture Search
• Are Labels Necessary for Neural Architecture Search?
• Task-Adaptive Neural Network Search with Meta-Contrastive Learning
• Learning Architectures for Binary Networks
• Rearchitecting Classification Frameworks For Increased Robustness
• Differentiable Sparsification for Deep Neural Networks
• MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
• TextNAS: A Neural Architecture Search Space tailored for Text Representation
• Rethinking Performance Estimation in Neural Architecture Search
• OnlineAugment: Online Data Augmentation with Less Domain Knowledge
• Privacy-preserving Collaborative Learning with Automatic Transformation Search
• Sample-Efficient Automated Deep Reinforcement Learning
• Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
• RSO: A Gradient Free Sampling Based Approach For Training Deep Neural Networks
• SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System
• Discovering Multi-Hardware Mobile Models via Architecture Search
• Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
• Genetic Neural Architecture Search for automatic assessment of human sperm images
• Intra-Ensemble in Neural Networks
• Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
• BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels
• Improve the performance of transfer learning without fine-tuning using dissimilarity-based multi-view learning for breast cancer histology images
• Trainless Model Performance Estimation for Neural Architecture Search
• LCP: A Low-Communication Parallelization Method for Fast Neural Network Inference in Image Recognition
• AutoSTR: Efficient Backbone Search for Scene Text Recognition
• Q-DeckRec: A Fast Deck Recommendation System for Collectible Card Games
• A Study on Encodings for Neural Architecture Search
• MobileDepth: Efficient Monocular Depth Prediction on Mobile Devices
• Fine-Grained Stochastic Architecture Search
• Efficient Architecture Search for Continual Learning
• Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification
• Benchmarking Automated Machine Learning Methods for Price Forecasting Applications
• Challenges for cognitive decoding using deep learning methods
• ConvNets vs. Transformers: Whose Visual Representations are More Transferable?
• AlphaNet: Improved Training of Supernets with Alpha-Divergence
• Accelerate CNN via Recursive Bayesian Pruning
• Automated Discovery of Adaptive Attacks on Adversarial Defenses
• Auto-Classifier: A Robust Defect Detector Based on an AutoML Head
• Dynamically Throttleable Neural Networks (TNN)
• Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks
• HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
• RepNAS: Searching for Efficient Re-parameterizing Blocks
• Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS)
• Binarized Neural Architecture Search for Efficient Object Recognition
• Slimmable Compressive Autoencoders for Practical Neural Image Compression
• A Learning-Based Tune-Free Control Framework for Large Scale Autonomous Driving System Deployment
• Video Action Recognition Via Neural Architecture Searching
• Latent Domain Learning with Dynamic Residual Adapters
• DC-NAS: Divide-and-Conquer Neural Architecture Search
• Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search
• Neural Architecture Search Over a Graph Search Space
• Single-Path Mobile AutoML: Efficient ConvNet Design and NAS Hyperparameter Optimization
• Generalizable Resource Allocation in Stream Processing via Deep Reinforcement Learning
• Layer Folding: Neural Network Depth Reduction using Activation Linearization
• Self-Assembling Modular Networks for Interpretable Multi-Hop Reasoning
• HyperSTAR: Task-Aware Hyperparameters for Deep Networks
• Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning
• MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records
• Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators
• AntMan: Sparse Low-Rank Compression to Accelerate RNN inference
• EPNAS: Efficient Progressive Neural Architecture Search
• Operation-level Progressive Differentiable Architecture Search
• Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
• Multi-Pass Transformer for Machine Translation
• Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach
• Learning Less-Overlapping Representations
• RePr: Improved Training of Convolutional Filters
• Generic Neural Architecture Search via Regression
• Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation
• Direct Output Connection for a High-Rank Language Model
• RT3D: Achieving Real-Time Execution of 3D Convolutional Neural Networks on Mobile Devices
• Binarized Neural Architecture Search
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution
• On the Bounds of Function Approximations
• Auptimizer -- an Extensible, Open-Source Framework for Hyperparameter Tuning
• RAPDARTS: Resource-Aware Progressive Differentiable Architecture Search
• Open Loop Hyperparameter Optimization and Determinantal Point Processes
• AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation
• Exploiting Operation Importance for Differentiable Neural Architecture Search
• Hydra: A Peer to Peer Distributed Training & Data Collection Framework
• Refining the Structure of Neural Networks Using Matrix Conditioning
• Disturbance-immune Weight Sharing for Neural Architecture Search
• Search to Distill: Pearls are Everywhere but not the Eyes
• Fisher Task Distance and Its Application in Neural Architecture Search
• Explore-Exploit: A Framework for Interactive and Online Learning
• AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
• Data-Driven Compression of Convolutional Neural Networks
• Fast Hardware-Aware Neural Architecture Search
• ResNetX: a more disordered and deeper network architecture
• Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
• Tiny Adversarial Mulit-Objective Oneshot Neural Architecture Search
• Efficient Neural Interaction Function Search for Collaborative Filtering
• DNQ: Dynamic Network Quantization
• Heuristic Rank Selection with Progressively Searching Tensor Ring Network
• StyleNAS: An Empirical Study of Neural Architecture Search to Uncover Surprisingly Fast End-to-End Universal Style Transfer Networks
• Effective, Efficient and Robust Neural Architecture Search
• AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles
• Piecewise Linear Units Improve Deep Neural Networks
• AutoTrans: Automating Transformer Design via Reinforced Architecture Search
• An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
• How Does Supernet Help in Neural Architecture Search?
• RandomNet: Towards Fully Automatic Neural Architecture Design for Multimodal Learning
• Neural Architecture Search for Gliomas Segmentation on Multimodal Magnetic Resonance Imaging
• Neighborhood-Aware Neural Architecture Search
• Single Person Pose Estimation: A Survey
• Transfer Learning for Multi-lingual Tasks -- a Survey
• Learned Indexes for Dynamic Workloads
• Improving Binary Neural Networks through Fully Utilizing Latent Weights
• Capacity allocation analysis of neural networks: A tool for principled architecture design
• Full-attention based Neural Architecture Search using Context Auto-regression
• NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters
• Parameter Prediction for Unseen Deep Architectures
• Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
• Learning Sparse Deep Feedforward Networks via Tree Skeleton Expansion
• Learning Graph Representation of Person-specific Cognitive Processes from Audio-visual Behaviours for Automatic Personality Recognition
• CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment
• WeNet: Weighted Networks for Recurrent Network Architecture Search
• Auto-Agent-Distiller: Towards Efficient Deep Reinforcement Learning Agents via Neural Architecture Search
• A Generative Model for Sampling High-Performance and Diverse Weights for Neural Networks
• MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning
• Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks
• DECORE: Deep Compression with Reinforcement Learning
• Direct Differentiable Augmentation Search
• Contrastive Embeddings for Neural Architectures
• Slot Machines: Discovering Winning Combinations of Random Weights in Neural Networks
• Neural Architecture Search with Random Labels
• Inception Convolution with Efficient Dilation Search
• Constrained Discrete Black-Box Optimization using Mixed-Integer Programming
• Efficient Scale-Permuted Backbone with Learned Resource Distribution
• G-DARTS-A: Groups of Channel Parallel Sampling with Attention
• Transfer Learning with Pre-trained Conditional Generative Models
• Analyzing the Expected Hitting Time of Evolutionary Computation-based Neural Architecture Search Algorithms
• Deep Reinforced Attention Learning for Quality-Aware Visual Recognition
• Representation Sharing for Fast Object Detector Search and Beyond
• Towards Diverse Perspective Learning with Selection over Multiple Temporal Poolings
• NeuroLGP-SM: Scalable Surrogate-Assisted Neuroevolution for Deep Neural Networks
• Hypernetwork-Based Augmentation
• Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularization
• Hyperparameter optimization with REINFORCE and Transformers
• Exploring the Loss Landscape in Neural Architecture Search
• Memory-Efficient Differentiable Transformer Architecture Search
• In folly ripe. In reason rotten. Putting machine theology to rest
• NeuroDB: A Neural Network Framework for Answering Range Aggregate Queries and Beyond
• ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection
• Efficient Neural Architecture Search with Performance Prediction
• Regularized Evolutionary Population-Based Training
• SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions
• Differentiable NAS Framework and Application to Ads CTR Prediction
• Neural Machine Translation: A Review and Survey
• FP-NAS: Fast Probabilistic Neural Architecture Search
• Searching for Accurate Binary Neural Architectures
• Understanding the Effects of Pre-Training for Object Detectors via Eigenspectrum
• Thanks for Nothing: Predicting Zero-Valued Activations with Lightweight Convolutional Neural Networks
• Memory-Efficient Hierarchical Neural Architecture Search for Image Denoising
• Single-level Optimization For Differential Architecture Search
• HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions
• Multi-objective Search of Robust Neural Architectures against Multiple Types of Adversarial Attacks
• Reinforcement Learning with Chromatic Networks for Compact Architecture Search
• NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition
• Bayesian Optimization with Approximate Set Kernels
• HAO: Hardware-aware neural Architecture Optimization for Efficient Inference
• TimeGate: Conditional Gating of Segments in Long-range Activities
• Sample Efficient Ensemble Learning with Catalyst.RL
• GEVO: GPU Code Optimization using Evolutionary Computation
• Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks
• Tuning a variational autoencoder for data accountability problem in the Mars Science Laboratory ground data system
• Expandable YOLO: 3D Object Detection from RGB-D Images
• RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flow
• ELASTIC: Improving CNNs with Dynamic Scaling Policies
• Yet Another Intermediate-Level Attack
• TEA-DNN: the Quest for Time-Energy-Accuracy Co-optimized Deep Neural Networks
• On the Orthogonality of Knowledge Distillation with Other Techniques: From an Ensemble Perspective
• ENAS4D: Efficient Multi-stage CNN Architecture Search for Dynamic Inference
• Model-Agnostic Meta-Learning using Runge-Kutta Methods
• Reinforcement Learning in R
• A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
• Efficient Semantic Segmentation using Gradual Grouping
• ImmuNetNAS: An Immune-network approach for searching Convolutional Neural Network Architectures
• URNet : User-Resizable Residual Networks with Conditional Gating Module
• DeepSwarm: Optimising Convolutional Neural Networks using Swarm Intelligence
• Learning to Cope with Adversarial Attacks
• Genetic Network Architecture Search
• Explaining Transition Systems through Program Induction
• Automated Problem Identification: Regression vs Classification via Evolutionary Deep Networks
• Using Program Induction to Interpret Transition System Dynamics
• Rotational Unit of Memory
• New Perspective of Interpretability of Deep Neural Networks
• Reducing Inference Latency with Concurrent Architectures for Image Recognition
• Efficient Model Performance Estimation via Feature Histories
• Pretraining Neural Architecture Search Controllers with Locality-based Self-Supervised Learning
• Meta-learning Transferable Representations with a Single Target Domain
• Mise en abyme with artificial intelligence: how to predict the accuracy of NN, applied to hyper-parameter tuning
• AutoPruning for Deep Neural Network with Dynamic Channel Masking
• Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems
• Graph Pruning for Model Compression
• Compact CNN Structure Learning by Knowledge Distillation
• Rapid Elastic Architecture Search under Specialized Classes and Resource Constraints
• Dynamic Routing Networks
• Deployment Optimization for Shared e-Mobility Systems with Multi-agent Deep Neural Search
• MLFriend: Interactive Prediction Task Recommendation for Event-Driven Time-Series Data
• EENA: Efficient Evolution of Neural Architecture
• A Genetic Algorithm based Kernel-size Selection Approach for a Multi-column Convolutional Neural Network
• Heart-Darts: Classification of Heartbeats Using Differentiable Architecture Search
• Improving the sample-efficiency of neural architecture search with reinforcement learning
• MONSTOR: An Inductive Approach for Estimating and Maximizing Influence over Unseen Networks
• Conceptual Expansion Neural Architecture Search (CENAS)
• Incorporating domain knowledge into neural-guided search
• Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach
• Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset
• The Effect of Data Ordering in Image Classification
• Multiple Myeloma Cancer Cell Instance Segmentation
• Rapid Model Architecture Adaption for Meta-Learning
• Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle
• WAS-VTON: Warping Architecture Search for Virtual Try-on Network
• Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
• FLASH: Fast Neural Architecture Search with Hardware Optimization
• Do CNNs Encode Data Augmentations?
• Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer
• Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
• Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification
• Composite Binary Decomposition Networks
• MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders
• SIPA: A Simple Framework for Efficient Networks
• Encoder-Decoder Neural Architecture Optimization for Keyword Spotting
• Deep Learning: Our Miraculous Year 1990-1991
• Integrating Multiple Receptive Fields through Grouped Active Convolution
• Network Architecture Search for Face Enhancement
• Disentangled Neural Architecture Search
• How Convolutional Neural Network Architecture Biases Learned Opponency and Colour Tuning
• Machine Learning Systems for Intelligent Services in the IoT: A Survey
• Developing Convolutional Neural Networks using a Novel Lamarckian Co-Evolutionary Algorithm
• RAM-NAS: Resource-aware Multiobjective Neural Architecture Search Method for Robot Vision Tasks
• Neural Parameter Allocation Search
• Adjoined Networks: A Training Paradigm with Applications to Network Compression
• A Roadmap for Robust End-to-End Alignment
• Neural Architecture Search as Sparse Supernet
• Rational Recurrences
• What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning
• FSD: Fully-Specialized Detector via Neural Architecture Search
• VeML: An End-to-End Machine Learning Lifecycle for Large-scale and High-dimensional Data
• AIPerf: Automated machine learning as an AI-HPC benchmark
• Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition
• FATNN: Fast and Accurate Ternary Neural Networks
• NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks
• Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS
• Fuzzy Logic Interpretation of Quadratic Networks
• Automated Deep Abstractions for Stochastic Chemical Reaction Networks
• Gator: Customizable Channel Pruning of Neural Networks with Gating
• Zero-Cost Operation Scoring in Differentiable Architecture Search
• EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch
• InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
• Neural Inheritance Relation Guided One-Shot Layer Assignment Search
• ADWPNAS: Architecture-Driven Weight Prediction for Neural Architecture Search
• Learning by Active Forgetting for Neural Networks
• AutoADR: Automatic Model Design for Ad Relevance
• Direct Federated Neural Architecture Search
• AutoSpeech 2020: The Second Automated Machine Learning Challenge for Speech Classification
• TND-NAS: Towards Non-differentiable Objectives in Progressive Differentiable NAS Framework
• GreedyNASv2: Greedier Search with a Greedy Path Filter
• Design of Artificial Intelligence Agents for Games using Deep Reinforcement Learning
• Mixed Variable Bayesian Optimization with Frequency Modulated Kernels
• Knowledge Transfer Graph for Deep Collaborative Learning
• Deep Neural Networks for Choice Analysis: Architectural Design with Alternative-Specific Utility Functions
• Evaluating Online and Offline Accuracy Traversal Algorithms for k-Complete Neural Network Architectures
• AutoML for Contextual Bandits
• Efficient Sampling for Predictor-Based Neural Architecture Search
• Towards Searching Efficient and Accurate Neural Network Architectures in Binary Classification Problems
• MS-DARTS: Mean-Shift Based Differentiable Architecture Search
• Adversarial Policy Gradient for Deep Learning Image Augmentation
• Network Clustering for Multi-task Learning
• Efficient falsification approach for autonomous vehicle validation using a parameter optimisation technique based on reinforcement learning
• Self-Reorganizing and Rejuvenating CNNs for Increasing Model Capacity Utilization
• Learning image quality assessment by reinforcing task amenable data selection
• Beyond Folklore: A Scaling Calculus for the Design and Initialization of ReLU Networks
• An Embedded Deep Learning based Word Prediction
• Distributed creation of Machine learning agents for Blockchain analysis
• Layout Design for Intelligent Warehouse by Evolution with Fitness Approximation
• PolyNeuron: Automatic Neuron Discovery via Learned Polyharmonic Spline Activations
• Transform-Based Feature Map Compression for CNN Inference
• Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures
• Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
• Neural Architecture Search via Bregman Iterations
• Jets and differential linear logic
• Trustless parallel local search for effective distributed algorithm discovery
• AmoebaContact and GDFold: a new pipeline for rapid prediction of protein structures
• Autoequivariant Network Search via Group Decomposition
• Efficient Structured Pruning and Architecture Searching for Group Convolution
• Evolutionary NAS with Gene Expression Programming of Cellular Encoding
• MOFA: Modular Factorial Design for Hyperparameter Optimization
• Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection
• Effective Model Compression via Stage-wise Pruning
• Understanding Cache Boundness of ML Operators on ARM Processors
• Structure Learning of Deep Neural Networks with Q-Learning
• MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing
• Learning sparse transformations through backpropagation
• Estimating air quality co-benefits of energy transition using machine learning
• Inner Ensemble Networks: Average Ensemble as an Effective Regularizer
• Tightening the Approximation Error of Adversarial Risk with Auto Loss Function Search
• Learnable Parameter Similarity
• Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
• PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search
• ConAM: Confidence Attention Module for Convolutional Neural Networks
• Building Sparse Deep Feedforward Networks using Tree Receptive Fields
• Patterns versus Characters in Subword-aware Neural Language Modeling
• $S^2$-LBI: Stochastic Split Linearized Bregman Iterations for Parsimonious Deep Learning
• ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
• A2: Extracting Cyclic Switchings from DOB-nets for Rejecting Excessive Disturbances
• One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking
• Deformable Stacked Structure for Named Entity Recognition
• Better Safe than Sorry: Evidence Accumulation Allows for Safe Reinforcement Learning
• Towards automated neural design: An open source, distributed neural architecture research framework
• Parameterless Stochastic Natural Gradient Method for Discrete Optimization and its Application to Hyper-Parameter Optimization for Neural Network
• Deep Learning Meets SAR
• Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement
• On-Policy Model Errors in Reinforcement Learning
• RNN-BOF: A Multivariate Global Recurrent Neural Network for Binary Outcome Forecasting of Inpatient Aggression
• Efficient Automatic Meta Optimization Search for Few-Shot Learning
• Photofeeler-D3: A Neural Network with Voter Modeling for Dating Photo Impression Prediction
• Prioritized Subnet Sampling for Resource-Adaptive Supernet Training
• Gradient-based Hyperparameter Optimization Over Long Horizons
• ISyNet: Convolutional Neural Networks design for AI accelerator
• Surrogate Model Based Hyperparameter Tuning for Deep Learning with SPOT
• RNN Architecture Learning with Sparse Regularization
• GPNAS: A Neural Network Architecture Search Framework Based on Graphical Predictor
• Seeing Convolution Through the Eyes of Finite Transformation Semigroup Theory: An Abstract Algebraic Interpretation of Convolutional Neural Networks
• Recommending Courses in MOOCs for Jobs: An Auto Weak Supervision Approach
• BNAS-v2: Memory-efficient and Performance-collapse-prevented Broad Neural Architecture Search
• Input-to-Output Gate to Improve RNN Language Models
• Automatically Designing CNN Architectures for Medical Image Segmentation
• Evolving Neural Architecture Using One Shot Model
• Neural Architecture Search with an Efficient Multiobjective Evolutionary Framework
• Channel Planting for Deep Neural Networks using Knowledge Distillation
• Understanding the wiring evolution in differentiable neural architecture search
• Auto Deep Compression by Reinforcement Learning Based Actor-Critic Structure
• Collaborative Group Learning
• DICE: Deep Significance Clustering for Outcome-Aware Stratification
• "You might also like this model": Data Driven Approach for Recommending Deep Learning Models for Unknown Image Datasets
• Segmentation of Objects by Hashing
• Enhanced Gradient for Differentiable Architecture Search
• Self-Constructing Neural Networks Through Random Mutation
• Knowledge Distillation By Sparse Representation Matching
• MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search
• ENOS: Energy-Aware Network Operator Search for Hybrid Digital and Compute-in-Memory DNN Accelerators
• Neural Architecture Search based on Cartesian Genetic Programming Coding Method
• Unchain the Search Space with Hierarchical Differentiable Architecture Search
• Grow-Push-Prune: aligning deep discriminants for effective structural network compression
• Vertex finding in neutrino-nucleus interaction: A Model Architecture Comparison
• Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS
• Making Differentiable Architecture Search less local
• NeuralArTS: Structuring Neural Architecture Search with Type Theory
• Balancing Accuracy and Latency in Multipath Neural Networks
• Communication-Efficient Separable Neural Network for Distributed Inference on Edge Devices
• Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search
• Functional Neural Networks for Parametric Image Restoration Problems
• AutoBSS: An Efficient Algorithm for Block Stacking Style Search
• Entropy Non-increasing Games for the Improvement of Dataflow Programming
• Third ArchEdge Workshop: Exploring the Design Space of Efficient Deep Neural Networks
• Improving Differentiable Architecture Search with a Generative Model
• ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network
• Learning What To Do by Simulating the Past
• Multi-Faceted Hierarchical Multi-Task Learning for a Large Number of Tasks with Multi-dimensional Relations
• A Neural Architecture Search based Framework for Liquid State Machine Design
• Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud
• BraidNet: procedural generation of neural networks for image classification problems using braid theory
• Fixed Priority Global Scheduling from a Deep Learning Perspective
• Out-of-the-box channel pruned networks
• Neural Plasticity Networks
• Generalized Reinforcement Meta Learning for Few-Shot Optimization
• Predicting the success of Gradient Descent for a particular Dataset-Architecture-Initialization (DAI)
• Learning, transferring, and recommending performance knowledge with Monte Carlo tree search and neural networks
• Architecture Agnostic Neural Networks
• Network representation learning: A macro and micro view
• Efficient Modelling Across Time of Human Actions and Interactions
• On the potential for open-endedness in neural networks
• Max and Coincidence Neurons in Neural Networks
• SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
• Rethinking Layer-wise Feature Amounts in Convolutional Neural Network Architectures
• CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks
• Neural Architecture Search in Embedding Space
• Self-Supervised Neural Architecture Search for Imbalanced Datasets
• Inferring Mesoscale Models of Neural Computation
• Neural Architecture Search in operational context: a remote sensing case-study
• Analyzing Neural Networks Based on Random Graphs
• DIVA: Dataset Derivative of a Learning Task
• Edge-featured Graph Neural Architecture Search
• MQGrad: Reinforcement Learning of Gradient Quantization in Parameter Server
• Scene-adaptive Knowledge Distillation for Sequential Recommendation via Differentiable Architecture Search
• Single-DARTS: Towards Stable Architecture Search
• FOX-NAS: Fast, On-device and Explainable Neural Architecture Search
• Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
• Knowledge accumulating: The general pattern of learning
• Learning Compatible Embeddings
• Learning to Transfer Learn: Reinforcement Learning-Based Selection for Adaptive Transfer Learning
• Coarse and fine-grained automatic cropping deep convolutional neural network
• Layer Flexible Adaptive Computational Time
• Not just about size - A Study on the Role of Distributed Word Representations in the Analysis of Scientific Publications
• Multi-Scale Spatially-Asymmetric Recalibration for Image Classification
• Network Space Search for Pareto-Efficient Spaces
• Automatic Machine Learning Derived from Scholarly Big Data
• T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging
• Multi-Objective DNN-based Precoder for MIMO Communications
• CUAB: Convolutional Uncertainty Attention Block Enhanced the Chest X-ray Image Analysis
• Automated Decision-based Adversarial Attacks
• Multi-headed Neural Ensemble Search
• Differentiable Architecture Pruning for Transfer Learning
• CompConv: A Compact Convolution Module for Efficient Feature Learning
• ML-misfit: Learning a robust misfit function for full-waveform inversion using machine learning
• Mutually-aware Sub-Graphs Differentiable Architecture Search
• MTL2L: A Context Aware Neural Optimiser
• Poisoning the Search Space in Neural Architecture Search
• Improving Generative Adversarial Networks with Local Coordinate Coding
• A Reinforcement Learning Approach for Sequential Spatial Transformer Networks
• Revisiting Neural Architecture Search
• Efficient Video Understanding via Layered Multi Frame-Rate Analysis
• LV-BERT: Exploiting Layer Variety for BERT
• Negotiating Team Formation Using Deep Reinforcement Learning