Neural Architecture Search: A Survey

Abstract

Deep Learning has enabled remarkable progress over the last years on a variety of tasks, such as image recognition, speech recognition, and machine translation. One crucial aspect for this progress are novel neural architectures. Currently employed architectures have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Because of this, there is growing interest in automated neural architecture search methods. We provide an overview of existing work in this field of research and categorize them according to three dimensions: search space, search strategy, and performance estimation strategy.

References in corpus (33)

• Auto-Encoding Variational Bayes
• LSTM: A Search Space Odyssey
• mixup: Beyond Empirical Risk Minimization
• Neural Architecture Search with Reinforcement Learning
• Improved Regularization of Convolutional Neural Networks with Cutout
• DARTS: Differentiable Architecture Search
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Rethinking the Value of Network Pruning
• AutoAugment: Learning Augmentation Policies from Data
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Designing Neural Network Architectures using Reinforcement Learning
• A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
• Xception: Deep Learning with Depthwise Separable Convolutions
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• Efficient Architecture Search by Network Transformation
• Shake-Shake regularization
• Random Search and Reproducibility for Neural Architecture Search
• Convolutional Neural Fabrics
• Path-Level Network Transformation for Efficient Architecture Search
• DeepArchitect: Automatically Designing and Training Deep Architectures
• N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning
• Freeze-Thaw Bayesian Optimization
• Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search
• MaskConnect: Connectivity Learning by Gradient Descent
• Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces
• From Nodes to Networks: Evolving Recurrent Neural Networks
• Transfer Learning with Neural AutoML
• Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing---and Back
• Connectivity Learning in Multi-Branch Networks
• Intriguing Properties of Adversarial Examples
• Learnable Embedding Space for Efficient Neural Architecture Compression
• Modularized Morphing of Neural Networks
• Learning to Design RNA

Cited by in corpus (343)

• AutoML: A Survey of the State-of-the-Art
• The Medical Segmentation Decathlon
• EfficientNetV2: Smaller Models and Faster Training
• Recent advances and clinical applications of deep learning in medical image analysis
• Medical Image Segmentation Using Deep Learning: A Survey
• Multi-Task Learning for Dense Prediction Tasks: A Survey
• Deep Learning Algorithms for Rotating Machinery Intelligent Diagnosis: An Open Source Benchmark Study
• A Survey on Evolutionary Neural Architecture Search
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better
• Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS
• A Review on Deep Learning in UAV Remote Sensing
• Optimization Problems for Machine Learning: A Survey
• ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
• Human-AI Collaboration in Data Science: Exploring Data Scientists' Perceptions of Automated AI
• Understanding and Robustifying Differentiable Architecture Search
• explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning
• Machine Learning for Microcontroller-Class Hardware: A Review
• Random Search and Reproducibility for Neural Architecture Search
• Machine-Learning-Based Diagnostics of EEG Pathology
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• Quantum agents in the Gym: a variational quantum algorithm for deep Q-learning
• Quantum circuit architecture search for variational quantum algorithms
• A Survey on Deep Learning for Skin Lesion Segmentation
• Bringing AI To Edge: From Deep Learning's Perspective
• Automated data processing and feature engineering for deep learning and big data applications: a survey
• MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers
• AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
• AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning
• Distributed intelligence on the Edge-to-Cloud Continuum: A systematic literature review
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• A Practical Survey on Faster and Lighter Transformers
• Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
• Edge Intelligence: Architectures, Challenges, and Applications
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• Review: Deep Learning in Electron Microscopy
• UncertaintyFuseNet: Robust Uncertainty-aware Hierarchical Feature Fusion Model with Ensemble Monte Carlo Dropout for COVID-19 Detection
• Stochastic analysis of heterogeneous porous material with modified neural architecture search (NAS) based physics-informed neural networks using transfer learning
• Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey
• Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments
• Recent Progress in the CUHK Dysarthric Speech Recognition System
• Neural Predictor based Quantum Architecture Search
• Learning to Optimize: A Primer and A Benchmark
• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• Neural Collaborative Reasoning
• General Purpose Artificial Intelligence Systems (GPAIS): Properties, Definition, Taxonomy, Societal Implications and Responsible Governance
• Deep Learning-Based Human Pose Estimation: A Survey
• Challenging the Security of Logic Locking Schemes in the Era of Deep Learning: A Neuroevolutionary Approach
• Auto-Keras: An Efficient Neural Architecture Search System
• Discovering Parametric Activation Functions
• TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training and Inference
• Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelines
• Deep Learning for Fine-Grained Image Analysis: A Survey
• Automated Machine Learning on Graphs: A Survey
• Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
• DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
• ASAP: Architecture Search, Anneal and Prune
• Auto-GNN: Neural Architecture Search of Graph Neural Networks
• Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook
• How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networks
• DAS-N2N: Machine learning Distributed Acoustic Sensing (DAS) signal denoising without clean data
• Artificial Intelligence in Glioma Imaging: Challenges and Advances
• AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning
• Evolving Normalization-Activation Layers
• Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
• EvoPruneDeepTL: An Evolutionary Pruning Model for Transfer Learning based Deep Neural Networks
• Dataset Condensation with Differentiable Siamese Augmentation
• RaLL: End-to-end Radar Localization on Lidar Map Using Differentiable Measurement Model
• NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search
• Toward Extremely Lightweight Distracted Driver Recognition With Distillation-Based Neural Architecture Search and Knowledge Transfer
• A Constructive Prediction of the Generalization Error Across Scales
• Towards Green Automated Machine Learning: Status Quo and Future Directions
• Auto-Ensemble: An Adaptive Learning Rate Scheduling based Deep Learning Model Ensembling
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search
• Quantum Embedding Search for Quantum Machine Learning
• AutoPrognosis 2.0: Democratizing Diagnostic and Prognostic Modeling in Healthcare with Automated Machine Learning
• A Comprehensive Review of Modern Object Segmentation Approaches
• Neural Architecture Search without Training
• ReLeQ: A Reinforcement Learning Approach for Deep Quantization of Neural Networks
• DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programs
• Neural Architecture Search For Keyword Spotting
• Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework
• Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
• $\text{FastSVD-ML-ROM}$: A Reduced-Order Modeling Framework based on Machine Learning for Real-Time Applications
• gLaSDI: Parametric Physics-informed Greedy Latent Space Dynamics Identification
• GaNDLF: A Generally Nuanced Deep Learning Framework for Scalable End-to-End Clinical Workflows in Medical Imaging
• Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
• Learning Deep Morphological Networks with Neural Architecture Search
• A fast multi-fidelity method with uncertainty quantification for complex data correlations: Application to vortex-induced vibrations of marine risers
• Using Convolutional Neural Networks to Develop Starting Models for 2D Full Waveform Inversion
• FLAML: A Fast and Lightweight AutoML Library
• Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?
• A Comprehensive Survey on Machine Learning Driven Material Defect Detection
• An AutoML-based Approach to Multimodal Image Sentiment Analysis
• FPUS23: An Ultrasound Fetus Phantom Dataset with Deep Neural Network Evaluations for Fetus Orientations, Fetal Planes, and Anatomical Features
• Evaluating Efficient Performance Estimators of Neural Architectures
• CryptoNAS: Private Inference on a ReLU Budget
• Pedestrian Attribute Recognition: A Survey
• FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
• Machine Learning with Confidential Computing: A Systematization of Knowledge
• Towards Battery-Free Machine Learning and Inference in Underwater Environments
• Triple-level Model Inferred Collaborative Network Architecture for Video Deraining
• Automated Architecture Design for Deep Neural Networks
• One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
• Sub-Architecture Ensemble Pruning in Neural Architecture Search
• Latency-Aware Differentiable Neural Architecture Search
• Pareto-Optimal Quantized ResNet Is Mostly 4-bit
• COVID-MobileXpert: On-Device COVID-19 Patient Triage and Follow-up using Chest X-rays
• How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS
• Autoencoding with a Classifier System
• Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices
• Overton: A Data System for Monitoring and Improving Machine-Learned Products
• Meta-Learning Symmetries by Reparameterization
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• NAS-FCOS: Fast Neural Architecture Search for Object Detection
• BioNetExplorer: Architecture-Space Exploration of Bio-Signal Processing Deep Neural Networks for Wearables
• Evaluating Generic Auto-ML Tools for Computational Pathology
• CODEBench: A Neural Architecture and Hardware Accelerator Co-Design Framework
• GraphPAS: Parallel Architecture Search for Graph Neural Networks
• Progressive DARTS: Bridging the Optimization Gap for NAS in the Wild
• Amplifying Pathological Detection in EEG Signaling Pathways through Cross-Dataset Transfer Learning
• Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey
• Differential Evolution for Neural Architecture Search
• Perceptron Theory Can Predict the Accuracy of Neural Networks
• Anomaly Detection with Score Distribution Discrimination
• Evolving Reinforcement Learning Algorithms
• Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directions
• Multiobjective Evolutionary Pruning of Deep Neural Networks with Transfer Learning for improving their Performance and Robustness
• Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
• How Powerful are Performance Predictors in Neural Architecture Search?
• Automated Concatenation of Embeddings for Structured Prediction
• Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels
• Self-supervised Cross-silo Federated Neural Architecture Search
• Neural Architecture Generator Optimization
• Flexible Dataset Distillation: Learn Labels Instead of Images
• A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition
• Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
• MoistNet: Machine Vision-based Deep Learning Models for Wood Chip Moisture Content Measurement
• Revisiting Meta-Learning as Supervised Learning
• Meta-learning curiosity algorithms
• Dynamic Hard Pruning of Neural Networks at the Edge of the Internet
• Evolutionary Neural Architecture Search Supporting Approximate Multipliers
• Error-feedback stochastic modeling strategy for time series forecasting with convolutional neural networks
• Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
• How to Train Your MAML to Excel in Few-Shot Classification
• Path homologies of deep feedforward networks
• One-Shot Neural Architecture Search via Compressive Sensing
• Multinomial Distribution Learning for Effective Neural Architecture Search
• Evolutionary Architecture Search for Graph Neural Networks
• Dataset Condensation with Distribution Matching
• Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding
• DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification
• Speedy Performance Estimation for Neural Architecture Search
• Saliency-Regularized Deep Multi-Task Learning
• To Share or Not To Share: A Comprehensive Appraisal of Weight-Sharing
• SparseBERT: Rethinking the Importance Analysis in Self-attention
• Learnable Embedding Space for Efficient Neural Architecture Compression
• Pose Neural Fabrics Search
• LightTrack: Finding Lightweight Neural Networks for Object Tracking via One-Shot Architecture Search
• Landing AI on Networks: An equipment vendor viewpoint on Autonomous Driving Networks
• Self-adaptive deep neural network: Numerical approximation to functions and PDEs
• Primer: Searching for Efficient Transformers for Language Modeling
• Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning
• Lifelong Learning of Compositional Structures
• Hybrid Parameter Search and Dynamic Model Selection for Mixed-Variable Bayesian Optimization
• Dynamic Structured Illumination Microscopy with a Neural Space-time Model
• GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet
• Computational Separation Between Convolutional and Fully-Connected Networks
• Differentiable architecture search with multi-dimensional attention for spiking neural networks
• Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search
• Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data
• A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction
• Optimal training of integer-valued neural networks with mixed integer programming
• Designing deep neural networks for driver intention recognition
• Sampled Training and Node Inheritance for Fast Evolutionary Neural Architecture Search
• HyperNOMAD: Hyperparameter optimization of deep neural networks using mesh adaptive direct search
• From Federated Learning to Federated Neural Architecture Search: A Survey
• NAS-VAD: Neural Architecture Search for Voice Activity Detection
• Fine-Grained Image Analysis with Deep Learning: A Survey
• SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials
• MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning
• Auto-PyTorch Tabular: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
• NAS-Navigator: Visual Steering for Explainable One-Shot Deep Neural Network Synthesis
• Activation Function Optimization Scheme for Image Classification
• Understanding Architectures Learnt by Cell-based Neural Architecture Search
• Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT Scans
• Automatic Fused Multimodal Deep Learning for Plant Identification
• Neural Architecture Search For Fault Diagnosis
• NASI: Label- and Data-agnostic Neural Architecture Search at Initialization
• CATE: Computation-aware Neural Architecture Encoding with Transformers
• Branched Multi-Task Networks: Deciding What Layers To Share
• AutoSF: Searching Scoring Functions for Knowledge Graph Embedding
• Physics-informed active learning with simultaneous weak-form latent space dynamics identification
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks
• Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation
• Approximate Computing and the Efficient Machine Learning Expedition
• Learning Personal Style from Few Examples
• S3NAS: Fast NPU-aware Neural Architecture Search Methodology
• DIFER: Differentiable Automated Feature Engineering
• Neural Architecture Search for Generative Adversarial Networks: A Comprehensive Review and Critical Analysis
• Semantic-Based Neural Network Repair
• ImmuNeCS: Neural Committee Search by an Artificial Immune System
• Backpropagation-Free 4D Continuous Ant-Based Neural Topology Search
• ApproxDet: Content and Contention-Aware Approximate Object Detection for Mobiles
• Collaborative Distillation for Ultra-Resolution Universal Style Transfer
• Seesaw-Net: Convolution Neural Network With Uneven Group Convolution
• AutoML to Date and Beyond: Challenges and Opportunities
• POPNASv2: An Efficient Multi-Objective Neural Architecture Search Technique
• AOGNets: Compositional Grammatical Architectures for Deep Learning
• Darts-Conformer: Towards Efficient Gradient-Based Neural Architecture Search For End-to-End ASR
• Model-based Deep Medical Imaging: the roadmap of generalizing iterative reconstruction model using deep learning
• VINNAS: Variational Inference-based Neural Network Architecture Search
• Neural network accelerator for quantum control
• Self-Organizing Intelligent Matter: A blueprint for an AI generating algorithm
• SOTERIA: In Search of Efficient Neural Networks for Private Inference
• Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
• Deep Learning and Traffic Classification: Lessons learned from a commercial-grade dataset with hundreds of encrypted and zero-day applications
• Hyperparameter Optimization Is Deceiving Us, and How to Stop It
• Convergence Properties of Stochastic Hypergradients
• RARTS: An Efficient First-Order Relaxed Architecture Search Method
• Neural Architecture Search in Graph Neural Networks
• An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization
• NAS-Count: Counting-by-Density with Neural Architecture Search
• Large-Scale Gradient-Free Deep Learning with Recursive Local Representation Alignment
• Post-synaptic potential regularization has potential
• Learning to Design RNA
• An Overview and Solution for Democratizing AI Workflows at the Network Edge
• AutoSTR: Efficient Backbone Search for Scene Text Recognition
• Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
• Intrinsic Dimension, Persistent Homology and Generalization in Neural Networks
• A Novel Training Protocol for Performance Predictors of Evolutionary Neural Architecture Search Algorithms
• Automated Discovery of Adaptive Attacks on Adversarial Defenses
• Intra-Ensemble in Neural Networks
• HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
• Trainless Model Performance Estimation for Neural Architecture Search
• Discovering Multi-Hardware Mobile Models via Architecture Search
• Inner-Imaging Networks: Put Lenses into Convolutional Structure
• Synthetic Petri Dish: A Novel Surrogate Model for Rapid Architecture Search
• Genetic Neural Architecture Search for automatic assessment of human sperm images
• Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification
• A Study on Encodings for Neural Architecture Search
• Learn Basic Skills and Reuse: Modularized Adaptive Neural Architecture Search (MANAS)
• Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering
• Differential Evolution Algorithm based Hyper-Parameters Selection of Convolutional Neural Network for Speech Command Recognition
• A Multi-objective Optimization Benchmark Test Suite for Real-time Semantic Segmentation
• Fitness Landscape Footprint: A Framework to Compare Neural Architecture Search Problems
• AIBench Training: Balanced Industry-Standard AI Training Benchmarking
• A Framework for End-to-End Learning on Semantic Tree-Structured Data
• Neighborhood-Aware Neural Architecture Search
• Improved Adversarial Training via Learned Optimizer
• Searching to Sparsify Tensor Decomposition for N-ary Relational Data
• AIO-P: Expanding Neural Performance Predictors Beyond Image Classification
• Exploiting Operation Importance for Differentiable Neural Architecture Search
• On the Bounds of Function Approximations
• AutoPilot: Automating SoC Design Space Exploration for SWaP Constrained Autonomous UAVs
• Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach
• Continual Learning: Tackling Catastrophic Forgetting in Deep Neural Networks with Replay Processes
• NeuronBlocks: Building Your NLP DNN Models Like Playing Lego
• ACDC: Weight Sharing in Atom-Coefficient Decomposed Convolution
• Automated Machine Learning Techniques for Data Streams
• Neural Group Testing to Accelerate Deep Learning
• Analyzing the Expected Hitting Time of Evolutionary Computation-based Neural Architecture Search Algorithms
• NASirt: AutoML based learning with instance-level complexity information
• Momentum Accelerates Evolutionary Dynamics
• Rethinking Neural Operations for Diverse Tasks
• SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning
• Hyperparameter optimization with REINFORCE and Transformers
• Exploring the Loss Landscape in Neural Architecture Search
• An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters
• Emulation with uncertainty quantification of regional sea-level change caused by the Antarctic Ice Sheet
• Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularization
• Derivation and Analysis of Fast Bilinear Algorithms for Convolution
• Ranking and Rejecting of Pre-Trained Deep Neural Networks in Transfer Learning based on Separation Index
• Evolutionary Cell Aided Design for Neural Network Architectures
• Reinforcement Learning with Chromatic Networks for Compact Architecture Search
• NASIB: Neural Architecture Search withIn Budget
• G-DARTS-A: Groups of Channel Parallel Sampling with Attention
• Simultaneously forecasting global geomagnetic activity using Recurrent Networks
• Efficient Incorporation of Multiple Latency Targets in the Once-For-All Network
• Multi-objective Evolutionary Algorithms are Generally Good: Maximizing Monotone Submodular Functions over Sequences
• Depth-Adaptive Neural Networks from the Optimal Control viewpoint
• Hyperparameter Optimization in Neural Networks via Structured Sparse Recovery
• A method for quantifying the generalization capabilities of generative models for solving Ising models
• AutoML for Contextual Bandits
• Optimal Transfer Learning Model for Binary Classification of Funduscopic Images through Simple Heuristics
• Correlation Analysis between the Robustness of Sparse Neural Networks and their Random Hidden Structural Priors
• Class-dependent Compression of Deep Neural Networks
• Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures
• What and Where: Learn to Plug Adapters via NAS for Multi-Domain Learning
• Evaluating Online and Offline Accuracy Traversal Algorithms for k-Complete Neural Network Architectures
• The Effect of Data Ordering in Image Classification
• MS-DARTS: Mean-Shift Based Differentiable Architecture Search
• Towards Cardiac Intervention Assistance: Hardware-aware Neural Architecture Exploration for Real-Time 3D Cardiac Cine MRI Segmentation
• Efficient Model Performance Estimation via Feature Histories
• Greedy Network Enlarging
• An Approximation Algorithm for Optimal Subarchitecture Extraction
• AIPerf: Automated machine learning as an AI-HPC benchmark
• New Perspective of Interpretability of Deep Neural Networks
• Token Pooling in Vision Transformers
• Negotiating Team Formation Using Deep Reinforcement Learning
• Lamina-specific neuronal properties promote robust, stable signal propagation in feedforward networks
• Learning What To Do by Simulating the Past
• Can a powerful neural network be a teacher for a weaker neural network?
• AutoCLINT: The Winning Method in AutoCV Challenge 2019
• Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection
• Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression
• Deep Learning Meets SAR
• Automatic Remaining Useful Life Estimation Framework with Embedded Convolutional LSTM as the Backbone
• AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation
• Scalable Hyperparameter Optimization with Lazy Gaussian Processes
• PEng4NN: An Accurate Performance Estimation Engine for Efficient Automated Neural Network Architecture Search
• Emergent Structures and Lifetime Structure Evolution in Artificial Neural Networks
• Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design
• Vertex finding in neutrino-nucleus interaction: A Model Architecture Comparison
• Mixed Precision DNN Qunatization for Overlapped Speech Separation and Recognition
• Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models
• Network representation learning: A macro and micro view
• Tetra-AML: Automatic Machine Learning via Tensor Networks
• Searching Search Spaces: Meta-evolving a Geometric Encoding for Neural Networks
• T-AutoML: Automated Machine Learning for Lesion Segmentation using Transformers in 3D Medical Imaging
• DIVA: Dataset Derivative of a Learning Task
• Evolutionary NAS with Gene Expression Programming of Cellular Encoding
• Activation functions enabling the addition of neurons and layers without altering outcomes
• Syno: Structured Synthesis for Neural Operators
• Analyzing Neural Networks Based on Random Graphs
• Towards One Shot Search Space Poisoning in Neural Architecture Search
• A Survey on Green Deep Learning
• Learning to Prevent Leakage: Privacy-Preserving Inference in the Mobile Cloud
• Accelerating Evolution Through Gene Masking and Distributed Search
• OpEvo: An Evolutionary Method for Tensor Operator Optimization
• Collaborative Pure Exploration in Kernel Bandit
• Periodic Spectral Ergodicity: A Complexity Measure for Deep Neural Networks and Neural Architecture Search
• Neural Twins Talk & Alternative Calculations
• Max and Coincidence Neurons in Neural Networks
• Augmented Data Science: Towards Industrialization and Democratization of Data Science
• Fixed Priority Global Scheduling from a Deep Learning Perspective
• A Neural Tangent Kernel Perspective of Infinite Tree Ensembles
• Evolving Neural Architecture Using One Shot Model
• Neural Architecture Search in Embedding Space
• Parametric machines: a fresh approach to architecture search
• VRoC: Variational Autoencoder-aided Multi-task Rumor Classifier Based on Text
• How to Train your DNN: The Network Operator Edition