TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Abstract

TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms. A computation expressed using TensorFlow can be executed with little or no change on a wide variety of heterogeneous systems, ranging from mobile devices such as phones and tablets up to large-scale distributed systems of hundreds of machines and thousands of computational devices such as GPU cards. The system is flexible and can be used to express a wide variety of algorithms, including training and inference algorithms for deep neural network models, and it has been used for conducting research and for deploying machine learning systems into production across more than a dozen areas of computer science and other fields, including speech recognition, computer vision, robotics, information retrieval, natural language processing, geographic information extraction, and computational drug discovery. This paper describes the TensorFlow interface and an implementation of that interface that we have built at Google. The TensorFlow API and a reference implementation were released as an open-source package under the Apache 2.0 license in November, 2015 and are available at www.tensorflow.org.

Version 2 updates only the metadata, to correct the formatting of Martín Abadi's name

References in corpus (12)

• Efficient Estimation of Word Representations in Vector Space
• Sequence to Sequence Learning with Neural Networks
• HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
• cuDNN: Efficient Primitives for Deep Learning
• One weird trick for parallelizing convolutional neural networks
• Multiple Object Recognition with Visual Attention
• Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks
• Massively Multitask Networks for Drug Discovery
• Grammar as a Foreign Language
• Massively Parallel Methods for Deep Reinforcement Learning
• Building high-level features using large scale unsupervised learning
• Move Evaluation in Go Using Deep Convolutional Neural Networks

Cited by in corpus (1505)

• A Survey on Deep Learning in Medical Image Analysis
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Deep Learning with Differential Privacy
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• An overview of gradient descent optimization algorithms
• Inductive Representation Learning on Large Graphs
• On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice
• The Kinetics Human Action Video Dataset
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
• GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification
• Conditional Image Generation with PixelCNN Decoders
• DeepDTA: Deep Drug-Target Binding Affinity Prediction
• Image reconstruction by domain transform manifold learning
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Deep learning for universal linear embeddings of nonlinear dynamics
• DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
• Understanding Black-box Predictions via Influence Functions
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models
• Deep Learning for Short-Term Traffic Flow Prediction
• DP-GEN: A concurrent learning platform for the generation of reliable deep learning based potential energy models
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
• Deep Learning-Based Communication Over the Air
• DUNet: A deformable network for retinal vessel segmentation
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Deep Audio-Visual Speech Recognition
• Density estimation using Real NVP
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities
• Embedding Watermarks into Deep Neural Networks
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
• Identification of heavy-flavour jets with the CMS detector in pp collisions at 13 TeV
• SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• Domain Separation Networks
• Deep Learning Methods for Improved Decoding of Linear Codes
• NiftyNet: a deep-learning platform for medical imaging
• Fully Dense UNet for 2D Sparse Photoacoustic Tomography Artifact Removal
• Large-Scale Evolution of Image Classifiers
• Learning to Detect
• Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures
• Horovod: fast and easy distributed deep learning in TensorFlow
• Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Wireless Image Transmission Using Deep Source Channel Coding With Attention Modules
• Deep reinforcement learning from human preferences
• A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
• Distributed Prioritized Experience Replay
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• Weakly-Supervised Convolutional Neural Networks for Multimodal Image Registration
• Unsupervised Learning of Probabilistic Diffeomorphic Registration for Images and Surfaces
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans
• Joint Classification and Prediction CNN Framework for Automatic Sleep Stage Classification
• HDLTex: Hierarchical Deep Learning for Text Classification
• DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• Generalized Unitary Coupled Cluster Wavefunctions for Quantum Computation
• Semi-supervised Deep Reinforcement Learning in Support of IoT and Smart City Services
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Transfer learning in hybrid classical-quantum neural networks
• Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
• Generalisation in humans and deep neural networks
• Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration
• Machine learning quantum phases of matter beyond the fermion sign problem
• DeepSeeNet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs
• Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
• DyNet: The Dynamic Neural Network Toolkit
• Hello Edge: Keyword Spotting on Microcontrollers
• Hindsight Experience Replay
• Bayesian Compression for Deep Learning
• Beyond Skip Connections: Top-Down Modulation for Object Detection
• A Review of automatic differentiation and its efficient implementation
• CrypTFlow2: Practical 2-Party Secure Inference
• GraphSAINT: Graph Sampling Based Inductive Learning Method
• Accelerating high-throughput virtual screening through molecular pool-based active learning
• Strawberry Fields: A Software Platform for Photonic Quantum Computing
• MR fingerprinting Deep RecOnstruction NEtwork (DRONE)
• Early Stage Malware Prediction Using Recurrent Neural Networks
• Facial Expression Recognition Using Enhanced Deep 3D Convolutional Neural Networks
• Sensitivity and Generalization in Neural Networks: an Empirical Study
• Causal Effect Inference with Deep Latent-Variable Models
• XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging
• Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
• Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
• Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising
• Learning Dexterous In-Hand Manipulation
• Attention-based Graph Neural Network for Semi-supervised Learning
• Var-CNN: A Data-Efficient Website Fingerprinting Attack Based on Deep Learning
• Reinforcement Learning with Augmented Data
• MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
• Learnable pooling with Context Gating for video classification
• Lunar Crater Identification via Deep Learning
• The Challenge of Non-Technical Loss Detection using Artificial Intelligence: A Survey
• Differentiable Programming Tensor Networks
• Source localization in an ocean waveguide using supervised machine learning
• Natural Language Inference over Interaction Space
• LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns
• Manifold: A Model-Agnostic Framework for Interpretation and Diagnosis of Machine Learning Models
• Real-time Neural-MPC: Deep Learning Model Predictive Control for Quadrotors and Agile Robotic Platforms
• Device Placement Optimization with Reinforcement Learning
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Dynamical heating across the Milky Way disc using APOGEE and $Gaia$
• Unsupervised Learning of Depth and Ego-Motion from Video
• Deep Neural Networks with Koopman Operators for Modeling and Control of Autonomous Vehicles
• GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation
• A feature agnostic approach for glaucoma detection in OCT volumes
• InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs
• Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
• Don't Use Large Mini-Batches, Use Local SGD
• DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars
• Local SGD Converges Fast and Communicates Little
• Generating Steganographic Images via Adversarial Training
• Software Engineering Challenges of Deep Learning
• Deep learning of multi-element abundances from high-resolution spectroscopic data
• Convolutional neural networks automate detection for tracking of submicron scale particles in 2D and 3D
• Pixels to Graphs by Associative Embedding
• ECG arrhythmia classification using a 2-D convolutional neural network
• Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
• GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoders
• Adversarial Training Methods for Semi-Supervised Text Classification
• Did you hear that? Adversarial Examples Against Automatic Speech Recognition
• Learning Depth from Single Images with Deep Neural Network Embedding Focal Length
• The Reversible Residual Network: Backpropagation Without Storing Activations
• URLNet: Learning a URL Representation with Deep Learning for Malicious URL Detection
• Synthetic Depth-of-Field with a Single-Camera Mobile Phone
• Anomaly Detection using One-Class Neural Networks
• A Bi-layered Parallel Training Architecture for Large-scale Convolutional Neural Networks
• Fathom: Reference Workloads for Modern Deep Learning Methods
• A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification
• Lifelong Learning with Dynamically Expandable Networks
• No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World
• A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards
• L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
• The Numerics of GANs
• Data Noising as Smoothing in Neural Network Language Models
• Differentiable Learning of Logical Rules for Knowledge Base Reasoning
• Seismic facies recognition based on prestack data using deep convolutional autoencoder
• Dynamical Variational Autoencoders: A Comprehensive Review
• Position Detection and Direction Prediction for Arbitrary-Oriented Ships via Multitask Rotation Region Convolutional Neural Network
• Detection of phase transition via convolutional neural network
• A Minimalist Approach to Offline Reinforcement Learning
• Physics-Informed Neural Networks for AC Optimal Power Flow
• A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis
• Simulator-free Solution of High-Dimensional Stochastic Elliptic Partial Differential Equations using Deep Neural Networks
• Deep-learning source localization using multi-frequency magnitude-only data
• Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning
• Understanding Membership Inferences on Well-Generalized Learning Models
• Towards More Accurate Automatic Sleep Staging via Deep Transfer Learning
• ProjE: Embedding Projection for Knowledge Graph Completion
• Embedding Projector: Interactive Visualization and Interpretation of Embeddings
• WideDTA: prediction of drug-target binding affinity
• DeepMood: Modeling Mobile Phone Typing Dynamics for Mood Detection
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Locating earthquakes with a network of seismic stations via a deep learning method
• Forecasting Future Humphrey Visual Fields Using Deep Learning
• Next Day Wildfire Spread: A Machine Learning Data Set to Predict Wildfire Spreading from Remote-Sensing Data
• Automated data processing and feature engineering for deep learning and big data applications: a survey
• Data-driven rogue waves and parameter discovery in the defocusing NLS equation with a potential using the PINN deep learning
• Tacotron: Towards End-to-End Speech Synthesis
• Adversarially-trained autoencoders for robust unsupervised new physics searches
• A Guide to Constraining Effective Field Theories with Machine Learning
• Deep Reinforcement Learning for Process Control: A Primer for Beginners
• CT sinogram-consistency learning for metal-induced beam hardening correction
• Neural Network Renormalization Group
• Cascaded Region-based Densely Connected Network for Event Detection: A Seismic Application
• BigDL: A Distributed Deep Learning Framework for Big Data
• Machine-learning-assisted correction of correlated qubit errors in a topological code
• A Survey of FPGA-Based Neural Network Accelerator
• PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting
• MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
• DeepArchitect: Automatically Designing and Training Deep Architectures
• InfoGAIL: Interpretable Imitation Learning from Visual Demonstrations
• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks
• Compacting, Picking and Growing for Unforgetting Continual Learning
• Self-supervised Learning of Motion Capture
• Physics-informed Neural Networks for Solving Nonlinear Diffusivity and Biot's equations
• IPOD: Intensive Point-based Object Detector for Point Cloud
• FigureQA: An Annotated Figure Dataset for Visual Reasoning
• Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
• Speedup for quantum optimal control from automatic differentiation based on graphics processing units
• Convolutional Sparse Support Estimator Based Covid-19 Recognition from X-ray Images
• Galaxy Morphology Classification with Deep Convolutional Neural Networks
• Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation
• What Sustained Multi-Disciplinary Research Can Achieve: The Space Weather Modeling Framework
• DARLA: Improving Zero-Shot Transfer in Reinforcement Learning
• Diffraction tomography with a deep image prior
• Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks
• Faint Repetitions from a Bright Fast Radio Burst Source
• Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
• GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks
• End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks
• Learning to Protect Communications with Adversarial Neural Cryptography
• Understanding Pooling in Graph Neural Networks
• End-to-End Differentiable Proving
• The Robust Manifold Defense: Adversarial Training using Generative Models
• COVID-19 Infection Map Generation and Detection from Chest X-Ray Images
• Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
• Recent Advances in Deep Learning: An Overview
• Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse models
• Machine learning of phase transitions in the percolation and XY models
• AtlFast3: the next generation of fast simulation in ATLAS
• LPRNet: License Plate Recognition via Deep Neural Networks
• Measurement of Anomalous Diffusion Using Recurrent Neural Networks
• TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network
• Contextual Hybrid Session-based News Recommendation with Recurrent Neural Networks
• Deep learning on fundus images detects glaucoma beyond the optic disc
• Learning to Reason: End-to-End Module Networks for Visual Question Answering
• AIDE: Fast and Communication Efficient Distributed Optimization
• Review: Deep Learning in Electron Microscopy
• Deep Learning-based Spacecraft Relative Navigation Methods: A Survey
• NSML: Meet the MLaaS platform with a real-world case study
• Machine learning applied to single-shot x-ray diagnostics in an XFEL
• Unsupervised Learning of Geometry with Edge-aware Depth-Normal Consistency
• Long-time predictive modeling of nonlinear dynamical systems using neural networks
• Not All Samples Are Created Equal: Deep Learning with Importance Sampling
• Multidimensional Contrast Limited Adaptive Histogram Equalization
• Classification of Machine Learning Frameworks for Data-Driven Thermal Fluid Models
• Male pelvic synthetic CT generation from T1-weighted MRI using 2D and 3D convolutional neural networks
• Outlier Exposure with Confidence Control for Out-of-Distribution Detection
• Limited View and Sparse Photoacoustic Tomography for Neuroimaging with Deep Learning
• Quantum Machine Learning for Particle Physics using a Variational Quantum Classifier
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• Newton vs the machine: solving the chaotic three-body problem using deep neural networks
• Neural Belief-Propagation Decoders for Quantum Error-Correcting Codes
• News Session-Based Recommendations using Deep Neural Networks
• Improving Landslide Detection on SAR Data through Deep Learning
• BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
• Multilevel domain decomposition-based architectures for physics-informed neural networks
• Deep Adaptive Learning for Writer Identification based on Single Handwritten Word Images
• Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
• Incremental Classifier Learning with Generative Adversarial Networks
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Classification of crystallization outcomes using deep convolutional neural networks
• Quantum algorithm for non-homogeneous linear partial differential equations
• Gradient-based optimal control of open quantum systems using quantum trajectories and automatic differentiation
• Customer Lifetime Value Prediction Using Embeddings
• Dynamic Routing Between Capsules
• Natural Language Generation for Electronic Health Records
• Unsupervised Heart-rate Estimation in Wearables With Liquid States and A Probabilistic Readout
• Feature visualization of Raman spectrum analysis with deep convolutional neural network
• Simultaneous Recognition and Pose Estimation of Instruments in Minimally Invasive Surgery
• Measurements of production cross sections of WZ and same-sign WW boson pairs in association with two jets in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Deep Learning for One-dimensional Consolidation
• Identifying Galaxy Mergers in Observations and Simulations with Deep Learning
• Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
• Learning hidden elasticity with deep neural networks
• Neural Models for Information Retrieval
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Deep learning in biomedical optics
• Measurement of the Higgs boson production rate in association with top quarks in final states with electrons, muons, and hadronically decaying tau leptons at $\sqrt{s}=$ 13 TeV
• A Survey on Spark Ecosystem for Big Data Processing
• Random Feature Expansions for Deep Gaussian Processes
• Universal Planning Networks
• Evolving Deep Convolutional Neural Networks for Image Classification
• Query-Reduction Networks for Question Answering
• A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
• Artificial Intelligence and its Role in Near Future
• CapsNet comparative performance evaluation for image classification
• Deep Bayesian Inversion
• Acoustic Hologram Optimisation Using Automatic Differentiation
• New high-quality strong lens candidates with deep learning in the Kilo Degree Survey
• Collaborative Deep Learning in Fixed Topology Networks
• Solving inverse-PDE problems with physics-aware neural networks
• LensExtractor: A Convolutional Neural Network in Search of Strong Gravitational Lenses
• Detection and Classification of Supernova Gravitational Waves Signals: A Deep Learning Approach
• Intelligent optical performance monitor using multi-task learning based artificial neural network
• Deep neural networks are robust to weight binarization and other non-linear distortions
• Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging utilizing Deep Learning
• Super-resolution reconstruction of turbulent flow at various Reynolds numbers based on generative adversarial networks
• SPECULATOR: Emulating stellar population synthesis for fast and accurate galaxy spectra and photometry
• A-NICE-MC: Adversarial Training for MCMC
• DLTK: State of the Art Reference Implementations for Deep Learning on Medical Images
• Unpaired image denoising using a generative adversarial network in X-ray CT
• Learning regression and verification networks for long-term visual tracking
• Machine Learning Uncertainties with Adversarial Neural Networks
• Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
• Reversible Architectures for Arbitrarily Deep Residual Neural Networks
• Physics-informed neural networks for solving parametric magnetostatic problems
• FontCode: Embedding Information in Text Documents using Glyph Perturbation
• Deep Learning Head Model for Real-time Estimation of Entire Brain Deformation in Concussion
• Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
• ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing
• NSML: A Machine Learning Platform That Enables You to Focus on Your Models
• ssEMnet: Serial-section Electron Microscopy Image Registration using a Spatial Transformer Network with Learned Features
• Causal Understanding of Fake News Dissemination on Social Media
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation
• Deep-Learning Convolutional Neural Networks for scattered shrub detection with Google Earth Imagery
• A Twofold Siamese Network for Real-Time Object Tracking
• cellSTORM - Cost-effective Super-Resolution on a Cellphone using dSTORM
• Population variability in the generation and thymic selection of T-cell repertoires
• Learning to Generalize from Sparse and Underspecified Rewards
• On-field player workload exposure and knee injury risk monitoring via deep learning
• Super-resolution emulator of cosmological simulations using deep physical models
• A robust anomaly finder based on autoencoders
• Accelerated multiscale mechanics modeling in a deep learning framework
• DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients with Advanced Nasopharyngeal Carcinoma using Pretreatment PET/CT
• A factorisation-aware Matrix element emulator
• A Machine Learning Framework for Real-time Inverse Modeling and Multi-objective Process Optimization of Composites for Active Manufacturing Control
• Semantic-aware Grad-GAN for Virtual-to-Real Urban Scene Adaption
• Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency
• Turbulent scalar flux in inclined jets in crossflow: counter gradient transport and deep learning modelling
• Asynchronous Decentralized Parallel Stochastic Gradient Descent
• A Study of BFLOAT16 for Deep Learning Training
• Multi-level Residual Networks from Dynamical Systems View
• Model calibration using ESEm v1.0.0 -- an open, scalable Earth System Emulator
• Co-training for Demographic Classification Using Deep Learning from Label Proportions
• Gap junction plasticity as a mechanism to regulate network-wide oscillations
• Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
• Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting
• Neural network decoder for topological color codes with circuit level noise
• Unveiling the Distinct Formation Pathways of the Inner and Outer Discs of the Milky Way with Bayesian Machine Learning
• Robust Federated Learning: The Case of Affine Distribution Shifts
• Accurate Real Time Localization Tracking in A Clinical Environment using Bluetooth Low Energy and Deep Learning
• Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon
• A Unified Optimization Approach for Sparse Tensor Operations on GPUs
• CLUE: A Chinese Language Understanding Evaluation Benchmark
• Statistical post-processing of wind speed forecasts using convolutional neural networks
• Memory Replay GANs: learning to generate images from new categories without forgetting
• Semantic Tagging with Deep Residual Networks
• Sobolev Training for Neural Networks
• Deep Learning Prediction of Adverse Drug Reactions Using Open TG-GATEs and FAERS Databases
• A Derivative-Free Method for Solving Elliptic Partial Differential Equations with Deep Neural Networks
• Quantum Graph Neural Networks
• Understanding Gradient Clipping in Private SGD: A Geometric Perspective
• Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes
• ConfusionFlow: A model-agnostic visualization for temporal analysis of classifier confusion
• Data-driven fluid mechanics of wind farms: A review
• ECHO: An Adaptive Orchestration Platform for Hybrid Dataflows across Cloud and Edge
• Learning phase transitions from dynamics
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• No Fuss Distance Metric Learning using Proxies
• Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation
• Towards better decoding and language model integration in sequence to sequence models
• Improving Fast Segmentation With Teacher-student Learning
• Data augmentation using learned transformations for one-shot medical image segmentation
• Sequence-to-sequence neural network models for transliteration
• Asymmetric Residual Neural Network for Accurate Human Activity Recognition
• Automatic construction of Chinese herbal prescription from tongue image via CNNs and auxiliary latent therapy topics
• STD: Sparse-to-Dense 3D Object Detector for Point Cloud
• A deep neural network to search for new long-lived particles decaying to jets
• SRECG: ECG Signal Super-resolution Framework for Portable/Wearable Devices in Cardiac Arrhythmias Classification
• PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
• Deep Learning as a Parton Shower
• Nowcasting-Nets: Deep Neural Network Structures for Precipitation Nowcasting Using IMERG
• Advance Warning Methodologies for COVID-19 using Chest X-Ray Images
• Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
• Reading Scene Text with Attention Convolutional Sequence Modeling
• Matter Power Spectrum Emulator for f(R) Modified Gravity Cosmologies
• Deep Direct Visual Odometry
• Chasing the impact of the Gaia-Sausage-Enceladus merger on the formation of the Milky Way thick disc
• Learning by Association - A versatile semi-supervised training method for neural networks
• Generation of abdominal synthetic CTs from 0.35T MR images using generative adversarial networks for MR-only liver radiotherapy
• Predicting atmospheric optical properties for radiative transfer computations using neural networks
• AIRNet: Self-Supervised Affine Registration for 3D Medical Images using Neural Networks
• Medical Imaging and Machine Learning
• Accelerating Recommendation System Training by Leveraging Popular Choices
• Binary MIMO Detection via Homotopy Optimization and Its Deep Adaptation
• Learning From Noisy Large-Scale Datasets With Minimal Supervision
• Neural Network Distiller: A Python Package For DNN Compression Research
• Multi-Generator Generative Adversarial Nets
• Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Early Myocardial Infarction Detection over Multi-view Echocardiography
• MoleculeNet: A Benchmark for Molecular Machine Learning
• DeepWarp: DNN-based Nonlinear Deformation
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• Doubly Stochastic Variational Inference for Deep Gaussian Processes
• Convolutional neural networks for atomistic systems
• SSGAN: Secure Steganography Based on Generative Adversarial Networks
• NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigm
• Automated detection of vulnerable plaque in intravascular ultrasound images
• Minimum Margin Loss for Deep Face Recognition
• Neural network reconstruction of the dense matter equation of state from neutron star observables
• Limits of End-to-End Learning
• Learning Gradient Descent: Better Generalization and Longer Horizons
• Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning
• Biased Importance Sampling for Deep Neural Network Training
• Search for electroweak production of charginos and neutralinos in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUs
• Using deep learning to understand and mitigate the qubit noise environment
• Introducing Representations of Facial Affect in Automated Multimodal Deception Detection
• Learn the new, keep the old: Extending pretrained models with new anatomy and images
• Predicting the Mechanical Properties of Biopolymer Gels Using Neural Networks Trained on Discrete Fiber Network Data
• Zero-Shot Learning by Generating Pseudo Feature Representations
• HKR For Handwritten Kazakh & Russian Database
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey
• Testing Convolutional Neural Networks for finding strong gravitational lenses in KiDS
• Deep Learning for Channel Sensing and Hybrid Precoding in TDD Massive MIMO OFDM Systems
• Clickbait Detection in Tweets Using Self-attentive Network
• RAPIDNN: In-Memory Deep Neural Network Acceleration Framework
• Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset
• Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)
• Deep Mutual Learning
• A Sparse Model-inspired Deep Thresholding Network for Exponential Signal Reconstruction -- Application in Fast Biological Spectroscopy
• Deep Efficient End-to-end Reconstruction (DEER) Network for Few-view Breast CT Image Reconstruction
• Uncovering Causality from Multivariate Hawkes Integrated Cumulants
• DeepTrend: A Deep Hierarchical Neural Network for Traffic Flow Prediction
• Combined searches for the production of supersymmetric top quark partners in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• MUVINE: Multi-stage Virtual Network Embedding in Cloud Data Centers using Reinforcement Learning based Predictions
• Photonic convolutional neural networks using integrated diffractive optics
• Sim2Real View Invariant Visual Servoing by Recurrent Control
• Semi-supervised Deep Kernel Learning: Regression with Unlabeled Data by Minimizing Predictive Variance
• Addressing Overfitting on Pointcloud Classification using Atrous XCRF
• Geometric deep learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity
• Indoor environment data time-series reconstruction using autoencoder neural networks
• pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis
• Learning Physical Graph Representations from Visual Scenes
• A Deep Policy Inference Q-Network for Multi-Agent Systems
• Parkinson's Disease Recognition Using SPECT Image and Interpretable AI: A Tutorial
• Towards End-to-End Code-Switching Speech Recognition
• AxoNet: an AI-based tool to count retinal ganglion cell axons
• Onsets and Frames: Dual-Objective Piano Transcription
• Learning the Effect of Registration Hyperparameters with HyperMorph
• A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
• Value Prediction Network
• IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
• Denoising Autoencoders for Overgeneralization in Neural Networks
• QRnet: optimal regulator design with LQR-augmented neural networks
• A scalable and fast artificial neural network syndrome decoder for surface codes
• Learning the Travelling Salesperson Problem Requires Rethinking Generalization
• Efficiently utilizing complex-valued PolSAR image data via a multi-task deep learning framework
• Painting halos from cosmic density fields of dark matter with physically motivated neural networks
• Transfer learning for radio galaxy classification
• Ensembles of Vision Transformers as a New Paradigm for Automated Classification in Ecology
• Capsule Networks with Max-Min Normalization
• Attentive Memory Networks: Efficient Machine Reading for Conversational Search
• Generative Adversarial Privacy
• Combining Background Subtraction Algorithms with Convolutional Neural Network
• Path Integral Networks: End-to-End Differentiable Optimal Control
• Dynamical mass inference of galaxy clusters with neural flows
• Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)
• Automated crater shape retrieval using weakly-supervised deep learning
• Flood-Filling Networks
• Relational Graph Convolutional Networks: A Closer Look
• SPP-Net: Deep Absolute Pose Regression with Synthetic Views
• Deep Interest Network for Click-Through Rate Prediction
• DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution
• From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
• Towards a Common Implementation of Reinforcement Learning for Multiple Robotic Tasks
• ZhuSuan: A Library for Bayesian Deep Learning
• Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization
• Image Processing Operations Identification via Convolutional Neural Network
• Adversarial Generation of Training Examples: Applications to Moving Vehicle License Plate Recognition
• A Survey of Machine Learning Methods and Challenges for Windows Malware Classification
• Visualizing probabilistic models: Intensive Principal Component Analysis
• LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations
• WHU-Stereo: A Challenging Benchmark for Stereo Matching of High-Resolution Satellite Images
• Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learning
• Hierarchical fuzzy neural networks with privacy preservation for heterogeneous big data
• Learning to Generate Corrective Patches using Neural Machine Translation
• A Comparison of Machine Learning Algorithms for the Surveillance of Autism Spectrum Disorder
• An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)
• Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
• Translating neutron star observations to nuclear symmetry energy via artificial neural networks
• Improving Massive MIMO Belief Propagation Detector with Deep Neural Network
• A Variational Bayesian Inference-Inspired Unrolled Deep Network for MIMO Detection
• Crowd Counting using Deep Recurrent Spatial-Aware Network
• MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
• Auto-weighted Robust Federated Learning with Corrupted Data Sources
• PHOTONAI -- A Python API for Rapid Machine Learning Model Development
• Ballistocardiogram artifact reduction in simultaneous EEG-fMRI using deep learning
• Scalable Learning of Non-Decomposable Objectives
• Machine Learning on Sequential Data Using a Recurrent Weighted Average
• In silico generation of novel, drug-like chemical matter using the LSTM neural network
• Extracting gamma-ray information from images with convolutional neural network methods on simulated Cherenkov Telescope Array data
• 'Skimming-Perusal' Tracking: A Framework for Real-Time and Robust Long-term Tracking
• A Deep Learning Approach for Pose Estimation from Volumetric OCT Data
• Quantifying Non-parametric Structure of High-redshift Galaxies with Deep Learning
• PHD-GIFs: Personalized Highlight Detection for Automatic GIF Creation
• Convolutional Neural Networks for Direct Detection of Dark Matter
• Pulsar Candidate Identification Using Semi-Supervised Generative Adversarial Networks
• Differentiable Molecular Simulations for Control and Learning
• A material decomposition method for dual-energy CT via dual interactive Wasserstein generative adversarial networks
• Incorporating physical constraints in a deep probabilistic machine learning framework for coarse-graining dynamical systems
• RIDDLE: Race and ethnicity Imputation from Disease history with Deep LEarning
• Declarative Recursive Computation on an RDBMS, or, Why You Should Use a Database For Distributed Machine Learning
• Observation of single top quark production in association with a Z boson in proton-proton collisions at $\sqrt{s}=$ 13 TeV
• End-to-End Adversarial Text-to-Speech
• The Synergy of Complex Event Processing and Tiny Machine Learning in Industrial IoT
• Mind the Pad -- CNNs can Develop Blind Spots
• The analysis of VERITAS muon images using convolutional neural networks
• Highly Scalable Image Reconstruction using Deep Neural Networks with Bandpass Filtering
• Towards Explainable Personalized Recommendations by Learning from Users' Photos
• Quantum Deep Reinforcement Learning for Robot Navigation Tasks
• Hyper-Molecules: on the Representation and Recovery of Dynamical Structures, with Application to Flexible Macro-Molecular Structures in Cryo-EM
• AIBench: An Industry Standard Internet Service AI Benchmark Suite
• Improving Variational Encoder-Decoders in Dialogue Generation
• Predicting quantum dynamical cost landscapes with deep learning
• Night Time Haze and Glow Removal using Deep Dilated Convolutional Network
• TensorLog: Deep Learning Meets Probabilistic DBs
• Deep Learning for Real-Time Aerodynamic Evaluations of Arbitrary Vehicle Shapes
• Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
• Enhancing Medical Image Registration via Appearance Adjustment Networks
• ZMCintegral: a Package for Multi-Dimensional Monte Carlo Integration on Multi-GPUs
• G-TADOC: Enabling Efficient GPU-Based Text Analytics without Decompression
• Pancreas Segmentation in CT and MRI Images via Domain Specific Network Designing and Recurrent Neural Contextual Learning
• Dim but not entirely dark: Extracting the Galactic Center Excess' source-count distribution with neural nets
• Looking Fast and Slow: Memory-Guided Mobile Video Object Detection
• Enforcing constraints for interpolation and extrapolation in Generative Adversarial Networks
• AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks
• Adaptive Gradient Quantization for Data-Parallel SGD
• Motif-based Convolutional Neural Network on Graphs
• High-fidelity Prediction of Megapixel Longitudinal Phase-space Images of Electron Beams using Encoder-Decoder Neural Networks
• Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification
• State Space LSTM Models with Particle MCMC Inference
• TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow
• A machine learning route between band mapping and band structure
• A Conditional Variational Framework for Dialog Generation
• The evolution of barred galaxies in the EAGLE simulations
• Scenario adaptive disruption prediction study for next generation burning-plasma tokamaks
• Understanding Synthetic Gradients and Decoupled Neural Interfaces
• Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese
• Pediatric Automatic Sleep Staging: A comparative study of state-of-the-art deep learning methods
• $\text{matryoshka}$: Halo Model Emulator for the Galaxy Power Spectrum
• Laplacian Smoothing Gradient Descent
• Deepr: A Convolutional Net for Medical Records
• The Lipschitz Constant of Self-Attention
• Negative Sampling Improves Hypernymy Extraction Based on Projection Learning
• Learning Markov Clustering Networks for Scene Text Detection
• BigDataBench: A Scalable and Unified Big Data and AI Benchmark Suite
• Earth System Data Cubes: Avenues for advancing Earth system research
• Multimodal Compact Bilinear Pooling for Multimodal Neural Machine Translation
• Explaining deep learning of galaxy morphology with saliency mapping
• CNNComparator: Comparative Analytics of Convolutional Neural Networks
• Wide Compression: Tensor Ring Nets
• Adaptive physics-informed neural operator for coarse-grained non-equilibrium flows
• Implementing graph neural networks with TensorFlow-Keras
• Efficient Winograd Convolution via Integer Arithmetic
• FabricNet: A Fiber Recognition Architecture Using Ensemble ConvNets
• On-the-fly Operation Batching in Dynamic Computation Graphs
• Enhance word representation for out-of-vocabulary on Ubuntu dialogue corpus
• Soft Sensing Transformer: Hundreds of Sensors are Worth a Single Word
• Treatment-Response Models for Counterfactual Reasoning with Continuous-time, Continuous-valued Interventions
• A Survey on Deep Learning Toolkits and Libraries for Intelligent User Interfaces
• Pseudogap Anderson impurity model out of equilibrium: A master equation tensor network approach
• Neural physical engines for inferring the halo mass distribution function
• Cross-Domain Object Detection Using Unsupervised Image Translation
• Machine learning identifies scale-free properties in disordered materials
• Understanding Hidden Memories of Recurrent Neural Networks
• Video Imagination from a Single Image with Transformation Generation
• Noise-resistant Deep Learning for Object Classification in 3D Point Clouds Using a Point Pair Descriptor
• A Survey of Deep Learning Techniques for Mobile Robot Applications
• A bio-inspired bistable recurrent cell allows for long-lasting memory
• A Framework for Parallel and Distributed Training of Neural Networks
• Automatic segmentation method of pelvic floor levator hiatus in ultrasound using a self-normalising neural network
• CHAOS: A Parallelization Scheme for Training Convolutional Neural Networks on Intel Xeon Phi
• Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
• Point Linking Network for Object Detection
• Dynamic Feature Acquisition Using Denoising Autoencoders
• Learning to solve inverse problems using Wasserstein loss
• Transferring Rich Deep Features for Facial Beauty Prediction
• A Convolutional Neural Network based Live Object Recognition System as Blind Aid
• Jet-Parton Assignment in ttH Events using Deep Learning
• Automatic detection of low surface brightness galaxies from SDSS images
• Parallelizing Linear Recurrent Neural Nets Over Sequence Length
• Finding Influential Instances for Distantly Supervised Relation Extraction
• SenseGen: A Deep Learning Architecture for Synthetic Sensor Data Generation
• Attention on Personalized Clinical Decision Support System: Federated Learning Approach
• Physics-informed neural networks for unsteady incompressible flows with time-dependent moving boundaries
• First results from the LUCID-Timepix spacecraft payload onboard the TechDemoSat-1 satellite in Low Earth Orbit
• Structure Inference Net: Object Detection Using Scene-Level Context and Instance-Level Relationships
• Multi-Source DOA Estimation through Pattern Recognition of the Modal Coherence of a Reverberant Soundfield
• Galaxy classification: deep learning on the OTELO and COSMOS databases
• Optimal Algorithms for Distributed Optimization
• Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments
• Deep learning and k-means clustering in heterotic string vacua with line bundles
• KOHTD: Kazakh Offline Handwritten Text Dataset
• Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
• Optimal Physical Preprocessing for Example-Based Super-Resolution
• No More Discrimination: Cross City Adaptation of Road Scene Segmenters
• FPGAs-as-a-Service Toolkit (FaaST)
• An Optimal Transport Approach to Personalized Federated Learning
• Machine Learning Product State Distributions from Initial Reactant States for a Reactive Atom-Diatom Collision System
• SemiFed: Semi-supervised Federated Learning with Consistency and Pseudo-Labeling
• Gradient Estimation with Stochastic Softmax Tricks
• A Light Dual-Task Neural Network for Haze Removal
• Improving Long-Horizon Forecasts with Expectation-Biased LSTM Networks
• A Novel Approach to Detect Phishing Attacks using Binary Visualisation and Machine Learning
• ElegansNet: a brief scientific report and initial experiments
• Autonomous Power Allocation based on Distributed Deep Learning for Device-to-Device Communication Underlaying Cellular Network
• Asynchronous Stochastic Gradient Descent with Variance Reduction for Non-Convex Optimization
• Systematic Weight Pruning of DNNs using Alternating Direction Method of Multipliers
• A convolutional neural network approach for reconstructing polarization information of photoelectric X-ray polarimeters
• A multi-branch convolutional neural network for detecting double JPEG compression
• Physics Constrained Learning for Data-driven Inverse Modeling from Sparse Observations
• Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions
• Derivative-Informed Projected Neural Networks for High-Dimensional Parametric Maps Governed by PDEs
• Modeling intermolecular and intramolecular modes of liquid water using multiple heat baths: Machine learning approach
• LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo
• Complex data labeling with deep learning methods: Lessons from fisheries acoustics
• Probabilistic Motion Modeling from Medical Image Sequences: Application to Cardiac Cine-MRI
• W-Net: A CNN-based Architecture for White Blood Cells Image Classification
• A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs
• Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships
• Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks
• C-LSTM: Enabling Efficient LSTM using Structured Compression Techniques on FPGAs
• Automatic detection of microsleep episodes with deep learning
• Human Gender Prediction Based on Deep Transfer Learning from Panoramic Radiograph Images
• Deep Stereo Matching with Explicit Cost Aggregation Sub-Architecture
• Using Spatio-temporal Deep Learning for Forecasting Demand and Supply-demand Gap in Ride-hailing System with Anonymised Spatial Adjacency Information
• A unified framework for 21cm tomography sample generation and parameter inference with Progressively Growing GANs
• Modeling Relationships in Referential Expressions with Compositional Modular Networks
• Deep Learning in Bioinformatics
• Robust Keystroke Biometric Anomaly Detection
• SoK: Privacy Preserving Machine Learning using Functional Encryption: Opportunities and Challenges
• Hybrid Classical/Machine-Learning Force Fields for the Accurate Description of Molecular Condensed-Phase Systems
• Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
• Quantifying the Preferential Direction of the Model Gradient in Adversarial Training With Projected Gradient Descent
• Facial Affect Estimation in the Wild Using Deep Residual and Convolutional Networks
• Illumination-aware Faster R-CNN for Robust Multispectral Pedestrian Detection
• Cloud2Edge Elastic AI Framework for Prototyping and Deployment of AI Inference Engines in Autonomous Vehicles
• Morphological Error Detection in 3D Segmentations
• MRI Tumor Segmentation with Densely Connected 3D CNN
• Dynamic Fusion Networks for Machine Reading Comprehension
• Machine Learning for Observables: Reactant to Product State Distributions for Atom-Diatom Collisions
• A Deep Double Ritz Method (D${}^2$RM) for solving Partial Differential Equations using Neural Networks
• NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition
• Direct Estimation of Porosity from Seismic Data using Rock and Wave Physics Informed Neural Networks (RW-PINN)
• A Comparative Taxonomy and Survey of Public Cloud Infrastructure Vendors
• Enhancing approximation abilities of neural networks by training derivatives
• Is Deep Reinforcement Learning Really Superhuman on Atari? Leveling the playing field
• Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines
• Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
• Searching for hot subdwarf stars from the LAMOST spectra. III. classifying the hot subdwarf stars from LAMOST DR4 using deep learning method
• A semi-supervised approach to dark matter searches in direct detection data with machine learning
• Search for $CP$ violation in ${\Xi }_b^{-}\to p{K}^{-}{K}^{-}$ decays
• Fast and Accurate Modeling of Transient-State Gradient-Spoiled Sequences by Recurrent Neural Networks
• Pose-adaptive Hierarchical Attention Network for Facial Expression Recognition
• On the Utility of Gradient Compression in Distributed Training Systems
• Malicious Code Detection: Run Trace Output Analysis by LSTM
• Efficient Parallel Translating Embedding For Knowledge Graphs
• A Marketplace for Data: An Algorithmic Solution
• Generative-based Airway and Vessel Morphology Quantification on Chest CT Images
• Social Bots for Online Public Health Interventions
• RAR-PINN algorithm for the data-driven vector-soliton solutions and parameter discovery of coupled nonlinear equations
• Predicting Adolescent Suicide Attempts with Neural Networks
• OpenML-Python: an extensible Python API for OpenML
• Physics-guided Convolutional Neural Network (PhyCNN) for Data-driven Seismic Response Modeling
• Accurate reconstruction of image stimuli from human fMRI based on the decoding model with capsule network architecture
• TTC: A Tensor Transposition Compiler for Multiple Architectures
• Next-Step Conditioned Deep Convolutional Neural Networks Improve Protein Secondary Structure Prediction
• Machine Learning Microscopic Form of Nematic Order in twisted double-bilayer graphene
• PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
• Adversary Detection in Neural Networks via Persistent Homology
• Asynchronous Parallel Bayesian Optimisation via Thompson Sampling
• Robust Lexical Features for Improved Neural Network Named-Entity Recognition
• Augmented Hard Example Mining for Generalizable Person Re-Identification
• Sinogram super-resolution and denoising convolutional neural network (SRCN) for limited data photoacoustic tomography
• Transformation Autoregressive Networks
• Utterance-level Aggregation For Speaker Recognition In The Wild
• NPBDREG: Uncertainty Assessment in Diffeomorphic Brain MRI Registration using a Non-parametric Bayesian Deep-Learning Based Approach
• Artificial Intelligence-Assisted Optimization and Multiphase Analysis of Polygon PEM Fuel Cells
• Advances in Deep Space Exploration via Simulators & Deep Learning
• Fast Reading Comprehension with ConvNets
• Evaluating deep variational autoencoders trained on pan-cancer gene expression
• Applying machine learning to the Calabi-Yau orientifolds with string vacua
• AI-Driven CT-based quantification, staging and short-term outcome prediction of COVID-19 pneumonia
• Inverse Modeling of Viscoelasticity Materials using Physics Constrained Learning
• tfp.mcmc: Modern Markov Chain Monte Carlo Tools Built for Modern Hardware
• Localized convolutional neural networks for geospatial wind forecasting
• Extract the energy scale of anomalous $\gamma \gamma \to W^{+}{W}^{-}$ scattering in the vector boson scattering process using artificial neural networks
• Ease.ml: Towards Multi-tenant Resource Sharing for Machine Learning Workloads
• Efficient and Deep Person Re-Identification using Multi-Level Similarity
• Optimal control for quantum detectors
• The Neutron Star Outer Crust Equation of State: A Machine Learning approach
• Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields
• Identification of Patterns in Cosmic-Ray Arrival Directions using Dynamic Graph Convolutional Neural Networks
• FreezeNet: Full Performance by Reduced Storage Costs
• Quantitative Comparison of Planar Coded Aperture Imaging Reconstruction Methods
• Accelerating PDE-constrained Inverse Solutions with Deep Learning and Reduced Order Models
• Can Active Memory Replace Attention?
• A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition
• Physics-informed deep learning for flow and deformation in poroelastic media
• Scaling Deep Learning-based Decoding of Polar Codes via Partitioning
• Masking by Moving: Learning Distraction-Free Radar Odometry from Pose Information
• The iNaturalist Species Classification and Detection Dataset
• Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products
• Probing effective field theory operators in the associated production of top quarks with a Z boson in multilepton final states at $\sqrt{s}=$ 13 TeV
• Semi-supervised learning based on generative adversarial network: a comparison between good GAN and bad GAN approach
• Energy Efficient Hadamard Neural Networks
• Artificial Neural Network Classification of 4FGL Sources
• Dynamics Transfer GAN: Generating Video by Transferring Arbitrary Temporal Dynamics from a Source Video to a Single Target Image
• Stochastic Neighbor Embedding separates well-separated clusters
• Solving for high dimensional committor functions using artificial neural networks
• ProLanGO: Protein Function Prediction Using Neural~Machine Translation Based on a Recurrent Neural Network
• Reynolds-Averaged Turbulence Modeling Using Type I and Type II Machine Learning Frameworks with Deep Learning
• Predictive data-driven model based on generative adversarial network for premixed turbulence-combustion regimes
• PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
• Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning
• A machine learning framework for LES closure terms
• LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks
• Learning to Sketch with Shortcut Cycle Consistency
• Adversarial Training for Disease Prediction from Electronic Health Records with Missing Data
• Deep learning for extracting protein-protein interactions from biomedical literature
• Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning
• ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Models
• Graph Neural Networks for reconstruction and classification in KM3NeT
• EffNet: An Efficient Structure for Convolutional Neural Networks
• Identifying the relevant dependencies of the neural network response on characteristics of the input space
• Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structure
• Precision medicine as a control problem: Using simulation and deep reinforcement learning to discover adaptive, personalized multi-cytokine therapy for sepsis
• Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features
• Intersymbolic AI: Interlinking Symbolic AI and Subsymbolic AI
• Asymmetrical estimator for training encapsulated deep photonic neural networks
• Machine learning in the study of phase transition of two-dimensional complex plasmas
• Unsupervised Learning from Continuous Video in a Scalable Predictive Recurrent Network
• Tangent: Automatic Differentiation Using Source Code Transformation in Python
• Collider signatures of vector-like fermions from a flavor symmetric model
• Image denoising and restoration with CNN-LSTM Encoder Decoder with Direct Attention
• Beyond optimization -- supervised learning applications in relativistic laser-plasma experiments
• Fully Automatic Wound Segmentation with Deep Convolutional Neural Networks
• C-RPNs: Promoting Object Detection in real world via a Cascade Structure of Region Proposal Networks
• From ionic surfactants to Nafion through convolutional neural networks
• Adversarial Attacks on Monocular Depth Estimation
• Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints
• Tails: Chasing Comets with the Zwicky Transient Facility and Deep Learning
• Machine learning enabled fast evaluation of dynamic aperture for storage ring accelerators
• Modulating and attending the source image during encoding improves Multimodal Translation
• Designing impact-resistant bio-inspired low-porosity structures using neural networks
• Multi-Task Learning for Arousal and Sleep Stage Detection Using Fully Convolutional Networks
• Sequence to Sequence Mixture Model for Diverse Machine Translation
• DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction
• Scaling End-to-End Models for Large-Scale Multilingual ASR
• Improving sensitivity of the ARIANNA detector by rejecting thermal noise with deep learning
• Visual Discovery at Pinterest
• StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction
• Dense Dilated UNet: Deep Learning for 3D Photoacoustic Tomography Image Reconstruction
• Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images
• Toward a Theory of Causation for Interpreting Neural Code Models
• RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks
• Motion Prediction Under Multimodality with Conditional Stochastic Networks
• Hand bone age estimation using divide and conquer strategy and lightweight convolutional neural networks
• Subaru Hyper Suprime-Cam revisits the large-scale environmental dependence on galaxy morphology over 360 deg${}^2$ at z=0.3-0.6
• Efficient MPS representations and quantum circuits from the Fourier modes of classical image data
• Three-dimensional convolutional neural networks for neutrinoless double-beta decay signal/background discrimination in high-pressure gaseous Time Projection Chamber
• What Catches the Eye? Visualizing and Understanding Deep Saliency Models
• Deep Neural Networks for Detecting Statistical Model Misspecifications. The Case of Measurement Invariance
• The problem of dust attenuation in photometric decomposition of edge-on galaxies and possible solutions
• Improved Hierarchical Patient Classification with Language Model Pretraining over Clinical Notes
• Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Prediction
• Transfer Learning for Neural Semantic Parsing
• New methods to assess and improve LIGO detector duty cycle
• Speed Benchmarking of Genetic Programming Frameworks
• Replay attack detection with complementary high-resolution information using end-to-end DNN for the ASVspoof 2019 Challenge
• RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification
• Quantifying Overheads in Charm++ and HPX using Task Bench
• Non-Determinism in TensorFlow ResNets
• Demystifying Differentiable Programming: Shift/Reset the Penultimate Backpropagator
• Predictive-State Decoders: Encoding the Future into Recurrent Networks
• Classifying the formation processes of S0 galaxies using Convolutional Neural Networks
• Learning Heuristic Search via Imitation
• Multi-Planar Deep Segmentation Networks for Cardiac Substructures from MRI and CT
• A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning
• On the generalizability of artificial neural networks in spin models
• FusionStitching: Boosting Memory Intensive Computations for Deep Learning Workloads
• Cross-domain Semantic Parsing via Paraphrasing
• Zero-Shot Sketch-Image Hashing
• Deep learning of deformation-dependent conductance in thin films: nanobubbles in graphene
• Joint Distributions for TensorFlow Probability
• Fast and effortless computation of profile likelihoods using CONNECT
• Momentum Residual Neural Networks
• Dual Network Architecture for Few-view CT -- Trained on ImageNet Data and Transferred for Medical Imaging
• Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
• A detailed comparative study of open source deep learning frameworks
• Acoustic scene classification using teacher-student learning with soft-labels
• Attentive Relational Networks for Mapping Images to Scene Graphs
• Automated Bridge Component Recognition using Video Data
• Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation
• A Human-Centered Machine-Learning Approach for Muscle-Tendon Junction Tracking in Ultrasound Images
• Unsupervised learning for concept detection in medical images: a comparative analysis
• Prediction of Influenza A virus infections in humans using an Artificial Neural Network learning approach
• Portable, high-performance containers for HPC
• Vector representations of text data in deep learning
• Towards Compact ConvNets via Structure-Sparsity Regularized Filter Pruning
• The redshift evolution of the S0 fraction for $z<1$ in COSMOS
• cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCL
• RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment
• A Deep Learning Approach for Determining Effects of Tuta Absoluta in Tomato Plants
• Multiple Instance Curriculum Learning for Weakly Supervised Object Detection
• A Collective Knowledge workflow for collaborative research into multi-objective autotuning and machine learning techniques
• ZMCintegral-v5: Support for Integrations with the Scanning of Large Parameter Grids on Multi-GPUs
• Predicting Different Types of Subtle Toxicity in Unhealthy Online Conversations
• Generating Neural Networks with Neural Networks
• L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout
• Dual Path Networks for Multi-Person Human Pose Estimation
• Recurrent Filter Learning for Visual Tracking
• Image Quality Assessment Guided Deep Neural Networks Training
• Toward Automatic Threat Recognition for Airport X-ray Baggage Screening with Deep Convolutional Object Detection
• Olive Oil is Made of Olives, Baby Oil is Made for Babies: Interpreting Noun Compounds using Paraphrases in a Neural Model
• Learning Online Alignments with Continuous Rewards Policy Gradient
• Seismic-Net: A Deep Densely Connected Neural Network to Detect Seismic Events
• Git Loss for Deep Face Recognition
• Semantic Refinement GRU-based Neural Language Generation for Spoken Dialogue Systems
• Related Pins at Pinterest: The Evolution of a Real-World Recommender System
• One-Class Feature Learning Using Intra-Class Splitting
• Deep learnig analysis of the inverse seesaw in a 3-3-1 model at the LHC
• Sequence-to-Sequence Forecasting-aided State Estimation for Power Systems
• Unsupervised Learning for Identifying Events in Active Target Experiments
• SleepMore: Inferring Sleep Duration at Scale via Multi-Device WiFi Sensing
• Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
• Acceleration Strategies for MR-STAT: Achieving High-Resolution Reconstructions on a Desktop PC within 3 minutes
• Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation
• Cardiac Segmentation from LGE MRI Using Deep Neural Network Incorporating Shape and Spatial Priors
• Language Style Transfer from Sentences with Arbitrary Unknown Styles
• Utilizing UNet for the future traffic map prediction task Traffic4cast challenge 2020
• ENG: End-to-end Neural Geometry for Robust Depth and Pose Estimation using CNNs
• HiveMind: A Scalable and Serverless Coordination Control Platform for UAV Swarms
• Can Neural Networks Understand Logical Entailment?
• Capsule Networks for Protein Structure Classification and Prediction
• Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducer
• A Dilated Inception Network for Visual Saliency Prediction
• KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation
• Flare: Native Compilation for Heterogeneous Workloads in Apache Spark
• Hull Form Optimization with Principal Component Analysis and Deep Neural Network
• Scaling GRPC Tensorflow on 512 nodes of Cori Supercomputer
• Reconstruction of 3-D Atomic Distortions from Electron Microscopy with Deep Learning
• AC/DC: In-Database Learning Thunderstruck
• An Adaptive X-vector Model for Text-independent Speaker Verification
• DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition
• Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model
• Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework
• Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraints
• CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms
• On Primal-Dual Approach for Distributed Stochastic Convex Optimization over Networks
• A Time Attention based Fraud Transaction Detection Framework
• Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems
• ModelHub.AI: Dissemination Platform for Deep Learning Models
• Siamese Neural Networks with Random Forest for detecting duplicate question pairs
• A Novel Multi-Task Tensor Correlation Neural Network for Facial Attribute Prediction
• Conditional Neural Process for non-parametric modeling of AGN light curve
• Learning Edge Properties in Graphs from Path Aggregations
• Fast Conditional Independence Test for Vector Variables with Large Sample Sizes
• Webly Supervised Learning for Skin Lesion Classification
• ParaDime: A Framework for Parametric Dimensionality Reduction
• Dynamic Hawkes Processes for Discovering Time-evolving Communities' States behind Diffusion Processes
• Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic models
• Mass Estimation of Planck Galaxy Clusters using Deep Learning
• Towards automated patient data cleaning using deep learning: A feasibility study on the standardization of organ labeling
• Sensing Higgs cascade decays through memory
• DNNVM : End-to-End Compiler Leveraging Heterogeneous Optimizations on FPGA-based CNN Accelerators
• Towards Better Analysis of Deep Convolutional Neural Networks
• Artificial Intelligence and Location Verification in Vehicular Networks
• Autoencoding sensory substitution
• Inhomogeneous Social Recommendation with Hypergraph Convolutional Networks
• Learning to Refine Human Pose Estimation
• Kronecker Recurrent Units
• Rethinking Machine Learning Development and Deployment for Edge Devices
• Improved particle-flow event reconstruction with scalable neural networks for current and future particle detectors
• OCoR: An Overlapping-Aware Code Retriever
• Fast Dynamic Routing Based on Weighted Kernel Density Estimation
• A Data and Model-Parallel, Distributed and Scalable Framework for Training of Deep Networks in Apache Spark
• Remote Sensing Image Fusion Based on Two-stream Fusion Network
• DMRO:A Deep Meta Reinforcement Learning-based Task Offloading Framework for Edge-Cloud Computing
• DeepWriting: Making Digital Ink Editable via Deep Generative Modeling
• LapTool-Net: A Contextual Detector of Surgical Tools in Laparoscopic Videos Based on Recurrent Convolutional Neural Networks
• Automatic breast cancer grading in lymph nodes using a deep neural network
• Efficient Palm-Line Segmentation with U-Net Context Fusion Module
• Performance Evaluation of Deep Learning Tools in Docker Containers
• nuts-flow/ml: data pre-processing for deep learning
• Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction
• A Bug or a Suggestion? An Automatic Way to Label Issues
• Deep 3D Convolutional Neural Network for Automated Lung Cancer Diagnosis
• GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB
• Hybrid Gradient Boosting Trees and Neural Networks for Forecasting Operating Room Data
• A Cross-Stitch Architecture for Joint Registration and Segmentation in Adaptive Radiotherapy
• Privacy-preserving Learning via Deep Net Pruning
• Identifying Exoplanets with Deep Learning. IV. Removing Stellar Activity Signals from Radial Velocity Measurements Using Neural Networks
• BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation
• SocialGuard: An Adversarial Example Based Privacy-Preserving Technique for Social Images
• Model-based Hand Pose Estimation for Generalized Hand Shape with Appearance Normalization
• Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks
• Multi-Atlas Segmentation and Spatial Alignment of the Human Embryo in First Trimester 3D Ultrasound
• An Unsupervised Deep Learning Approach for Scenario Forecasts
• BUSU-Net: An Ensemble U-Net Framework for Medical Image Segmentation
• Compressed Sensing: From Research to Clinical Practice with Data-Driven Learning
• Neural Networks for Encoding Dynamic Security-Constrained Optimal Power Flow
• Inference with Artificial Neural Networks on Analog Neuromorphic Hardware
• Gradient Masking and the Underestimated Robustness Threats of Differential Privacy in Deep Learning
• Meta-learnt priors slow down catastrophic forgetting in neural networks
• Predicting risk of late age-related macular degeneration using deep learning
• Soli-enabled Noncontact Heart Rate Detection for Sleep and Meditation Tracking
• Orders-of-magnitude speedup in atmospheric chemistry modeling through neural network-based emulation
• Machine Learning and Location Verification in Vehicular Networks
• Byte-based Language Identification with Deep Convolutional Networks
• Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval
• Why not be Versatile? Applications of the SGNMT Decoder for Machine Translation
• Designing a Micro-Benchmark Suite to Evaluate gRPC for TensorFlow: Early Experiences
• Deep Subspace Clustering Networks
• Deep Tensor Convolution on Multicores
• Maximum Entropy Flow Networks
• A Deep Learning based Framework to Detect and Recognize Humans using Contactless Palmprints in the Wild
• Training Keyword Spotters with Limited and Synthesized Speech Data
• Cascaded channel pruning using hierarchical self-distillation
• Improving Proton Dose Calculation Accuracy by Using Deep Learning
• GPflux: A Library for Deep Gaussian Processes
• Beyond Fine Tuning: A Modular Approach to Learning on Small Data
• Residual Squeeze VGG16
• Rethinking Floating Point Overheads for Mixed Precision DNN Accelerators
• Identifying Potential Exomoon Signals with Convolutional Neural Networks
• Very Deep Convolutional Neural Networks for Raw Waveforms
• Neural Networks for Beginners. A fast implementation in Matlab, Torch, TensorFlow
• The GPU Phase Folding and Deep Learning Method for Detecting Exoplanet Transits
• Noise-robust latent vector reconstruction in ptychography using deep generative models
• Weakly-Supervised Anomaly Detection in the Milky Way
• SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning
• Gaussian Constrained Attention Network for Scene Text Recognition
• Deep Adversarial Transition Learning using Cross-Grafted Generative Stacks
• Rethinking Recurrent Neural Networks and Other Improvements for Image Classification
• FusionLane: Multi-Sensor Fusion for Lane Marking Semantic Segmentation Using Deep Neural Networks
• Surrogate Optimization of Deep Neural Networks for Groundwater Predictions
• A Smart Security System with Face Recognition
• Image Captioning Based on a Hierarchical Attention Mechanism and Policy Gradient Optimization
• ReHAR: Robust and Efficient Human Activity Recognition
• Open Set Chinese Character Recognition using Multi-typed Attributes
• Robust Automatic Whole Brain Extraction on Magnetic Resonance Imaging of Brain Tumor Patients using Dense-Vnet
• Physics-informed neural network applied to surface-tension-driven liquid film flows
• Reconstruction of $\tau$ lepton pair invariant mass using an artificial neural network
• SERKET: An Architecture for Connecting Stochastic Models to Realize a Large-Scale Cognitive Model
• Simplified End-to-End MMI Training and Voting for ASR
• Fast Certified Robust Training with Short Warmup
• Metric Learning-based Generative Adversarial Network
• Real-time visual tracking by deep reinforced decision making
• A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis
• Optimized higher-order photon state classification by machine learning
• An Attention-Based Deep Generative Model for Anomaly Detection in Industrial Control Systems
• VEGA: Towards an End-to-End Configurable AutoML Pipeline
• Fusarium Damaged Kernels Detection Using Transfer Learning on Deep Neural Network Architecture
• Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?
• Auto-Vectorizing TensorFlow Graphs: Jacobians, Auto-Batching And Beyond
• A light neural network for modulation detection under impairments
• Origins of Extragalactic Cosmic Ray Nuclei by Contracting Alignment Patterns induced in the Galactic Magnetic Field
• DA-RNN: Semantic Mapping with Data Associated Recurrent Neural Networks
• MUFold-SS: Protein Secondary Structure Prediction Using Deep Inception-Inside-Inception Networks
• Word Sense Disambiguation with LSTM: Do We Really Need 100 Billion Words?
• Machine learning-based vorticity evolution and superresolution of homogeneous isotropic turbulence using wavelet projection
• DensSiam: End-to-End Densely-Siamese Network with Self-Attention Model for Object Tracking
• Neural Network Training as an Optimal Control Problem: An Augmented Lagrangian Approach
• Revisiting Flow Information for Traffic Prediction
• Information-Theoretic Visual Explanation for Black-Box Classifiers
• Traffic map prediction using UNet based deep convolutional neural network
• Combining high-performance hardware, cloud computing, and deep learning frameworks to accelerate physical simulations: probing the Hopfield network
• Gaussian Gated Linear Networks
• Enabling Embedded Inference Engine with ARM Compute Library: A Case Study
• Learning Sampling Policies for Domain Adaptation
• Learning Embodied Semantics via Music and Dance Semiotic Correlations
• Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework
• MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Image
• Helix: Holistic Optimization for Accelerating Iterative Machine Learning
• Machine Learning Post-Minkowskian Integrals
• An Attention Mechanism for Answer Selection Using a Combined Global and Local View
• Learning deep abdominal CT registration through adaptive loss weighting and synthetic data generation
• Multiple Description Convolutional Neural Networks for Image Compression
• An Accelerated Analog Neuromorphic Hardware System Emulating NMDA- and Calcium-Based Non-Linear Dendrites
• DLR : Toward a deep learned rhythmic representation for music content analysis
• Going faster to see further: GPU-accelerated value iteration and simulation for perishable inventory control using JAX
• Predicting Short Term Energy Demand in Smart Grid: A Deep Learning Approach for Integrating Renewable Energy Sources in Line with SDGs 7, 9, and 13
• Ad-Net: Audio-Visual Convolutional Neural Network for Advertisement Detection In Videos
• A morphological segmentation approach to determining bar lengths
• Anomaly detection in Astrophysics: a comparison between unsupervised Deep and Machine Learning on KiDS data
• MILDNet: A Lightweight Single Scaled Deep Ranking Architecture
• Toward Scalable Machine Learning and Data Mining: the Bioinformatics Case
• Unsupervised Data Imputation via Variational Inference of Deep Subspaces
• TrICy: Trigger-guided Data-to-text Generation with Intent aware Attention-Copy
• The Reincarnation of Grille Cipher: A Generative Approach
• Outage-Watch: Early Prediction of Outages using Extreme Event Regularizer
• Portable learning environments for hands-on computational instruction: Using container- and cloud-based technology to teach data science
• Classifier and Exemplar Synthesis for Zero-Shot Learning
• Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis
• ORIGAMI: A Heterogeneous Split Architecture for In-Memory Acceleration of Learning
• Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps
• Embarrassingly Simple Binary Representation Learning
• Discriminative Mutual Information Estimators for Channel Capacity Learning
• Auxiliary Multimodal LSTM for Audio-visual Speech Recognition and Lipreading
• A Machine Learning Approach to Classify Kinematics and Vortex Wake Modes of Oscillating Foils
• Diversity/Parallelism Trade-off in Distributed Systems with Redundancy
• An Orchestrated Empirical Study on Deep Learning Frameworks and Platforms
• Design Rule Violation Hotspot Prediction Based on Neural Network Ensembles
• Video Saliency Detection by 3D Convolutional Neural Networks
• Improving Source Separation via Multi-Speaker Representations
• Retrosynthesis with Attention-Based NMT Model and Chemical Analysis of the "Wrong" Predictions
• DeepBeat: A multi-task deep learning approach to assess signal quality and arrhythmia detection in wearable devices
• NUQSGD: Provably Communication-efficient Data-parallel SGD via Nonuniform Quantization
• When Fashion Meets Big Data: Discriminative Mining of Best Selling Clothing Features
• Unsupervised Deep-Learning Based Deformable Image Registration: A Bayesian Framework
• Learning long-term dependencies for action recognition with a biologically-inspired deep network
• AI Tax: The Hidden Cost of AI Data Center Applications
• Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
• Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
• Geometric Prediction: Moving Beyond Scalars
• Knowledge Fusion via Embeddings from Text, Knowledge Graphs, and Images
• Dark Matter Subhalos, Strong Lensing and Machine Learning
• UV-GAN: Adversarial Facial UV Map Completion for Pose-invariant Face Recognition
• CNN Acceleration by Low-rank Approximation with Quantized Factors
• A comparable study of modeling units for end-to-end Mandarin speech recognition
• Visualizing the Hidden Features of Galaxy Morphology with Machine Learning
• Bridging the Gap Between Neural Networks and Neuromorphic Hardware with A Neural Network Compiler
• An Attention-Based Approach for Single Image Super Resolution
• SAIFE: Unsupervised Wireless Spectrum Anomaly Detection with Interpretable Features
• LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation
• Deep Learning in Robotics: A Review of Recent Research
• Generalization and Robustness Implications in Object-Centric Learning
• Auto-Encoding Twin-Bottleneck Hashing
• Adversarial Image Alignment and Interpolation
• Locally Adaptive Learning Loss for Semantic Image Segmentation
• A Neural-Network-defined Gaussian Mixture Model for particle identification applied to the LHCb fixed-target programme
• Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems
• Improving Performance of End-to-End ASR on Numeric Sequences
• Convolutional Sparse Support Estimator Network (CSEN) From energy efficient support estimation to learning-aided Compressive Sensing
• Who said that?: Audio-visual speaker diarisation of real-world meetings
• Data-Centric Engineering: integrating simulation, machine learning and statistics. Challenges and Opportunities
• Mixed Diagnostics for Longitudinal Properties of Electron Bunches in a Free-Electron Laser
• Machine learning methods for Schlieren imaging of a plasma channel in tenuous atomic vapor
• PulseDL-II: A System-on-Chip Neural Network Accelerator for Timing and Energy Extraction of Nuclear Detector Signals
• 2D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloud
• SparCE: Sparsity aware General Purpose Core Extensions to Accelerate Deep Neural Networks
• A Comparison of Hybrid and End-to-End Models for Syllable Recognition
• Automated Artery Localization and Vessel Wall Segmentation of Magnetic Resonance Vessel Wall Images using Tracklet Refinement and Polar Conversion
• Training Optimus Prime, M.D.: Generating Medical Certification Items by Fine-Tuning OpenAI's gpt2 Transformer Model
• Improving Semantic Segmentation via Dilated Affinity
• The use of adversaries for optimal neural network training
• Accelerating temporal action proposal generation via high performance computing
• A Diffusion Approximation Theory of Momentum SGD in Nonconvex Optimization
• Meta Dropout: Learning to Perturb Features for Generalization
• Accelerating Backward Aggregation in GCN Training with Execution Path Preparing on GPUs
• Exploration of Convolutional Neural Network Architectures for Large Region Map Automation
• The Mason-Alberta Phonetic Segmenter: A forced alignment system based on deep neural networks and interpolation
• Measuring the Substructure Mass Power Spectrum of 23 SLACS Strong Galaxy-Galaxy Lenses with Convolutional Neural Networks
• Supervised Dimensionality Reduction for Big Data
• Machine-learning a virus assembly fitness landscape
• Point-to-Pose Voting based Hand Pose Estimation using Residual Permutation Equivariant Layer
• A citizen-science approach to muon events in imaging atmospheric Cherenkov telescope data: the Muon Hunter
• AccelAT: A Framework for Accelerating the Adversarial Training of Deep Neural Networks through Accuracy Gradient
• A Novel Speech-Driven Lip-Sync Model with CNN and LSTM
• Distributed Deep Learning in Open Collaborations
• The Impact of Reinitialization on Generalization in Convolutional Neural Networks
• MMGAN: Manifold Matching Generative Adversarial Network
• Phonetic Word Embeddings
• A Cascaded Residual UNET for Fully Automated Segmentation of Prostate and Peripheral Zone in T2-weighted 3D Fast Spin Echo Images
• A Deep Reinforcement Learning Based Multi-Criteria Decision Support System for Textile Manufacturing Process Optimization
• Big Data application in congestion detection and classification using Apache spark
• On the Convergence of Step Decay Step-Size for Stochastic Optimization
• Towards Accurate Predictions and Causal 'What-if' Analyses for Planning and Policy-making: A Case Study in Emergency Medical Services Demand
• Dual-energy CT imaging from single-energy CT data with material decomposition convolutional neural network
• Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets
• Fine-Grained Stochastic Architecture Search
• Joint Network based Attention for Action Recognition
• Probabilistic Neural Programs
• Short utterance compensation in speaker verification via cosine-based teacher-student learning of speaker embeddings
• RL STaR Platform: Reinforcement Learning for Simulation based Training of Robots
• Adaptive Fusion for RGB-D Salient Object Detection
• On-Policy Trust Region Policy Optimisation with Replay Buffers
• DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency
• Prediction Model for Semitransparent Watercolor Pigment Mixtures Using Deep Learning with a Dataset of Transmittance and Reflectance
• Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables
• TauRieL: Targeting Traveling Salesman Problem with a deep reinforcement learning inspired architecture
• Large-Scale YouTube-8M Video Understanding with Deep Neural Networks
• MPIgnite: An MPI-Like Language and Prototype Implementation for Apache Spark
• Finding Likely Errors with Bayesian Specifications
• Recovering Homography from Camera Captured Documents using Convolutional Neural Networks
• Predicting Natural Hazards with Neuronal Networks
• Capsule networks for low-data transfer learning
• Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
• Equivalence of Dataflow Graphs via Rewrite Rules Using a Graph-to-Sequence Neural Model
• A General Approach for Using Deep Neural Network for Digital Watermarking
• Cost-Effective Federated Learning Design
• AI Driven Knowledge Extraction from Clinical Practice Guidelines: Turning Research into Practice
• Model-Free Renewable Scenario Generation Using Generative Adversarial Networks
• Level generation and style enhancement -- deep learning for game development overview
• Logical Reasoning for Revealing the Critical Temperature through Deep Learning of Configuration Ensemble of Statistical Systems
• Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases
• Unsupervised MRI Super-Resolution Using Deep External Learning and Guided Residual Dense Network with Multimodal Image Priors
• A low-rank representation for unsupervised registration of medical images
• Supervised Learning and Reinforcement Learning of Feedback Models for Reactive Behaviors: Tactile Feedback Testbed
• Combinatory Adjoints and Differentiation
• Nonlinear Conjugate Gradients For Scaling Synchronous Distributed DNN Training
• Online Multi-Object Tracking with Dual Matching Attention Networks
• Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation
• Towards a Better Match in Siamese Network Based Visual Object Tracker
• Machine learning based event reconstruction for the MUonE experiment
• Narrowing the discovery space of the cosmological 21-cm signal using multi-wavelength constraints
• Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning
• Using graph neural networks to reconstruct charged pion showers in the CMS High Granularity Calorimeter
• swCaffe: a Parallel Framework for Accelerating Deep Learning Applications on Sunway TaihuLight
• Spatial Mapping with Gaussian Processes and Nonstationary Fourier Features
• AIBench Scenario: Scenario-distilling AI Benchmarking
• Particle identification with machine learning from incomplete data in the ALICE experiment
• Halo Properties from Observable Measures of Environment: I. Halo and Subhalo Masses
• Load-Balanced Sparse MTTKRP on GPUs
• Label-free timing analysis of SiPM-based modularized detectors with physics-constrained deep learning
• WSNet: Compact and Efficient Networks Through Weight Sampling
• A Methodological Review of Visual Road Recognition Procedures for Autonomous Driving Applications
• Group Anomaly Detection using Deep Generative Models
• Progressive Learning of Low-Precision Networks
• On Learning High Dimensional Structured Single Index Models
• Multi-Mention Learning for Reading Comprehension with Neural Cascades
• COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compression
• An Asymptotic Analysis of Minibatch-Based Momentum Methods for Linear Regression Models
• Learning Channel Inter-dependencies at Multiple Scales on Dense Networks for Face Recognition
• Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs
• An Actor-Critic-Attention Mechanism for Deep Reinforcement Learning in Multi-view Environments
• Deformable Registration Using Average Geometric Transformations for Brain MR Images
• Predictive Coding-based Deep Dynamic Neural Network for Visuomotor Learning
• Detecting Adversarial Perturbations with Saliency
• An online sequence-to-sequence model for noisy speech recognition
• Research on Gender-related Fingerprint Features
• Visual Tracking via Dynamic Memory Networks
• Opportunistic Emulation of Computationally Expensive Simulations via Deep Learning
• Attaining human-level performance with atlas location autocontext for anatomical landmark detection in 3D CT data
• Character-Level Feature Extraction with Densely Connected Networks
• Face Recognition in Unconstrained Conditions: A Systematic Review
• NeuralLog: a Neural Logic Language
• Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units
• ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction
• Confined Gradient Descent: Privacy-preserving Optimization for Federated Learning
• Finding Person Relations in Image Data of the Internet Archive
• Improved Meta-Learning Training for Speaker Verification
• Knowledge-and-Data-Driven Amplitude Spectrum Prediction for Hierarchical Neural Vocoders
• Channel-Driven Monte Carlo Sampling for Bayesian Distributed Learning in Wireless Data Centers
• Discriminative Multi-modality Speech Recognition
• Filtering Variational Objectives
• Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorization
• A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
• Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring
• Demand Forecasting for Platelet Usage: from Univariate Time Series to Multivariate Models
• Modeling and simulating the excited-state dynamics of a system with condensed phases: A machine learning approach
• Trusted Neural Networks for Safety-Constrained Autonomous Control
• Arbitrary Discrete Sequence Anomaly Detection with Zero Boundary LSTM
• Stein Variational Gaussian Processes
• Capacity-Approaching Autoencoders for Communications
• A novel combination of theoretical analysis and data-driven method for reconstruction of structural defects
• Neural Aesthetic Image Reviewer
• AIBench Training: Balanced Industry-Standard AI Training Benchmarking
• Residual Encoder-Decoder Network for Deep Subspace Clustering
• Deep Equal Risk Pricing of Financial Derivatives with Multiple Hedging Instruments
• Adaptive Synthetic Characters for Military Training
• Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment
• DALiuGE: A Graph Execution Framework for Harnessing the Astronomical Data Deluge
• Luandri: a Clean Lua Interface to the Indri Search Engine
• Bringing Impressionism to Life with Neural Style Transfer in Come Swim
• Neural Machine Translation with Characters and Hierarchical Encoding
• Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with Satellite Imagery
• Autonomous driving challenge: To Infer the property of a dynamic object based on its motion pattern using recurrent neural network
• Obtaining Accurate Probabilistic Causal Inference by Post-Processing Calibration
• Semi-Supervised Learning via New Deep Network Inversion
• CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior
• Reasoning about Fine-grained Attribute Phrases using Reference Games
• Using Program Induction to Interpret Transition System Dynamics
• Deep Learning: Generalization Requires Deep Compositional Feature Space Design
• Character-Based Text Classification using Top Down Semantic Model for Sentence Representation
• Explaining Transition Systems through Program Induction
• Discriminative Learning for Monaural Speech Separation Using Deep Embedding Features
• On the notion of number in humans and machines
• Brain MR Image Segmentation in Small Dataset with Adversarial Defense and Task Reorganization
• Applying Generative Adversarial Networks to Intelligent Subsurface Imaging and Identification
• Large Scale Incremental Learning
• Multitask Text-to-Visual Embedding with Titles and Clickthrough Data
• Group Emotion Recognition Using Machine Learning
• Processing-In-Memory Acceleration of Convolutional Neural Networks for Energy-Efficiency, and Power-Intermittency Resilience
• Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks
• DETECT: Deep Trajectory Clustering for Mobility-Behavior Analysis
• CNN-LSTM models for Multi-Speaker Source Separation using Bayesian Hyper Parameter Optimization
• Learning Hidden Dynamics using Intelligent Automatic Differentiation
• Restyling Data: Application to Unsupervised Domain Adaptation
• Self-Supervised Learning and Prediction of Microstructure Evolution with Recurrent Neural Networks
• DeepVA: Bridging Cognition and Computation through Semantic Interaction and Deep Learning
• Breaking Moravec's Paradox: Visual-Based Distribution in Smart Fashion Retail
• Match${}^2$: A Matching over Matching Model for Similar Question Identification
• tfShearlab: The TensorFlow Digital Shearlet Transform for Deep Learning
• Parallel Programming Models for Heterogeneous Many-Cores : A Survey
• Theory-Guided Machine Learning for Process Simulation of Advanced Composites
• Leveraging Multi-domain, Heterogeneous Data using Deep Multitask Learning for Hate Speech Detection
• AdeNet: Deep learning architecture that identifies damaged electrical insulators in power lines
• A character representation enhanced on-device Intent Classification
• Model Optimization for Deep Space Exploration via Simulators and Deep Learning
• Comparing the costs of abstraction for DL frameworks
• Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
• Distributed Deep Reinforcement Learning: An Overview
• A Better and Faster End-to-End Model for Streaming ASR
• Neural Networks with Inputs Based on Domain of Dependence and A Converging Sequence for Solving Conservation Laws, Part I: 1D Riemann Problems
• VTLayout: Fusion of Visual and Text Features for Document Layout Analysis
• Plan-Based Relaxed Reward Shaping for Goal-Directed Tasks
• BCNet: A Deep Convolutional Neural Network for Breast Cancer Grading
• The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
• CausCF: Causal Collaborative Filtering for RecommendationEffect Estimation
• Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
• Designing A Clinically Applicable Deep Recurrent Model to Identify Neuropsychiatric Symptoms in People Living with Dementia Using In-Home Monitoring Data
• Real-Time Cell Sorting with Scalable In Situ FPGA-Accelerated Deep Learning
• Machine Learning in Gamma Astronomy
• Simmering: Sufficient is better than optimal for training neural networks
• $\overline{\text{D}}$arkRayNet: Emulation of cosmic-ray antideuteron fluxes from dark matter
• Investigating Resource-efficient Neutron/Gamma Classification ML Models Targeting eFPGAs
• PycWB: A User-friendly, Modular, and Python-based Framework for Gravitational Wave Unmodelled Search
• Heterogeneous Visible-Thermal and Visible-Infrared Face Recognition using Unit-Class Loss and Cross-Modality Discriminator
• Analytic Correlation of Inflationary Potential to Power Spectrum Shape: Limits of Validity, and `No-Go' for Small Field Model Analytics
• Quantitative Parametric Mapping of Tissues Properties from Standard Magnetic Resonance Imaging Enabled by Deep Learning
• Transient Stability Analysis with Physics-Informed Neural Networks
• The use of Generative Adversarial Networks to characterise new physics in multi-lepton final states at the LHC
• cuConv: A CUDA Implementation of Convolution for CNN Inference
• EmpLite: A Lightweight Sequence Labeling Model for Emphasis Selection of Short Texts
• Aerial Height Prediction and Refinement Neural Networks with Semantic and Geometric Guidance
• Towards constraining triple gluon operators through tops
• Implicit Feedback Deep Collaborative Filtering Product Recommendation System
• Deep Learning for Distributed Channel Feedback and Multiuser Precoding in FDD Massive MIMO
• Adaptive Periodic Averaging: A Practical Approach to Reducing Communication in Distributed Learning
• Dynamic Sparsity Neural Networks for Automatic Speech Recognition
• A Hybrid-Order Distributed SGD Method for Non-Convex Optimization to Balance Communication Overhead, Computational Complexity, and Convergence Rate
• Towards Time-Aware Context-Aware Deep Trust Prediction in Online Social Networks
• Deploying Deep Ranking Models for Search Verticals
• Smaller Models, Better Generalization
• Inference of visual field test performance from OCT volumes using deep learning
• NPTC-net: Narrow-Band Parallel Transport Convolutional Neural Network on Point Clouds
• LAGC: Lazily Aggregated Gradient Coding for Straggler-Tolerant and Communication-Efficient Distributed Learning
• Fast Adjustable Threshold For Uniform Neural Network Quantization (Winning solution of LPIRC-II)
• Anomaly Detection and Correction in Large Labeled Bipartite Graphs
• Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization
• Extreme Classification in Log Memory
• Learning Discriminators as Energy Networks in Adversarial Learning
• MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation
• Optimization of hybrid parallel application execution in heterogeneous high performance computing systems considering execution time and power consumption
• Audio Based Disambiguation Of Music Genre Tags
• Towards a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection
• Adversarial Attack Type I: Cheat Classifiers by Significant Changes
• Face-Cap: Image Captioning using Facial Expression Analysis
• Deep Sequence Learning with Auxiliary Information for Traffic Prediction
• Adversarial Training for Patient-Independent Feature Learning with IVOCT Data for Plaque Classification
• Hierarchical Transfer Convolutional Neural Networks for Image Classification
• Fine-Grained Energy and Performance Profiling framework for Deep Convolutional Neural Networks
• S4Net: Single Stage Salient-Instance Segmentation
• Deep Compressive Macroscopic Fluorescence Lifetime Imaging
• A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation
• Attention-Based End-to-End Speech Recognition on Voice Search
• Integrating Deep Learning in Domain Sciences at Exascale
• Experiential Robot Learning with Accelerated Neuroevolution
• Training DNNs in O(1) memory with MEM-DFA using Random Matrices
• Dropout against Deep Leakage from Gradients
• Flow field tomography with uncertainty quantification using a Bayesian physics-informed neural network
• WOMBAT: A fully Bayesian global flux-inversion framework
• Learning-based Motion Artifact Removal Networks (LEARN) for Quantitative $R_2^{\ast }$ Mapping
• Muon Identification Using Deep Neural Networks with the Muon Telescope Detector at STAR
• Infinite-Task Learning with RKHSs
• On Label Shift in Domain Adaptation via Wasserstein Distance
• Learning Higher-Order Dynamics in Video-Based Cardiac Measurement
• Out-of-focus: Learning Depth from Image Bokeh for Robotic Perception
• Iterative Multi-document Neural Attention for Multiple Answer Prediction
• PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence
• Automated Meta-Analysis: A Causal Learning Perspective
• Bellman: A Toolbox for Model-Based Reinforcement Learning in TensorFlow
• Detection and Classification of Breast Cancer Metastates Based on U-Net
• Simultaneous Denoising and Dereverberation Using Deep Embedding Features
• Painting Many Pasts: Synthesizing Time Lapse Videos of Paintings
• Acoustic feature learning using cross-domain articulatory measurements
• Adversarial Learning for Supervised and Semi-supervised Relation Extraction in Biomedical Literature
• CDC: Classification Driven Compression for Bandwidth Efficient Edge-Cloud Collaborative Deep Learning
• Symmetrical Synthesis for Deep Metric Learning
• Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels
• Review and Prospect: Deep Learning in Nuclear Magnetic Resonance Spectroscopy
• OD-SGD: One-step Delay Stochastic Gradient Descent for Distributed Training
• ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes
• Deep Reinforcement Learning for Active Human Pose Estimation
• DaSGD: Squeezing SGD Parallelization Performance in Distributed Training Using Delayed Averaging
• DEED: A General Quantization Scheme for Communication Efficiency in Bits
• Principled learning method for Wasserstein distributionally robust optimization with local perturbations
• Regularly Updated Deterministic Policy Gradient Algorithm
• FastVentricle: Cardiac Segmentation with ENet
• Single-channel Speech Dereverberation via Generative Adversarial Training
• MvMM-RegNet: A new image registration framework based on multivariate mixture model and neural network estimation
• End-to-End Interpretation of the French Street Name Signs Dataset
• Predictive Uncertainty through Quantization
• Online Detection of Action Start in Untrimmed, Streaming Videos
• Compressing Sign Information in DCT-based Image Coding via Deep Sign Retrieval
• CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
• Deep learning-based Fast Volumetric Image Generation for Image-guided Proton FLASH Radiotherapy
• Introduction to a novel T2 relaxation analysis method SAME-ECOS: Spectrum Analysis for Multiple Exponentials via Experimental Condition Oriented Simulation
• Mixed-Resolution Image Representation and Compression with Convolutional Neural Networks
• Framework for Designing Filters of Spectral Graph Convolutional Neural Networks in the Context of Regularization Theory
• Function Preserving Projection for Scalable Exploration of High-Dimensional Data
• Cribriform pattern detection in prostate histopathological images using deep learning models
• Towards Relevance and Sequence Modeling in Language Recognition
• The Deep Poincaré Map: A Novel Approach for Left Ventricle Segmentation
• CupNet -- Pruning a network for geometric data
• D-ACC: Dynamic Adaptive Cruise Control for Highways with Ramps Based on Deep Q-Learning
• Speeding-up Age Estimation in Intelligent Demographics System via Network Optimization
• Predict joint angle of body parts based on sequence pattern recognition
• Towards Understanding the Information Ecosystem Through the Lens of Multiple Web Communities
• Rapid Identification of X-ray Diffraction Spectra Based on Very Limited Data by Interpretable Convolutional Neural Networks
• On the Existence of Logarithmic Terms in the Drag Coefficient and Nusselt Number of a Single Sphere at High Reynolds Numbers
• Radio Halo Detection in MWA Data using Deep Neural Networks and Generative Data Augmentation
• Differential cross section measurements of top quark pair production for variables of the dineutrino system with the CMS experiment
• Energy Correction in Reduced SiD Electromagnetic Calorimeter
• AIBench: An Agile Domain-specific Benchmarking Methodology and an AI Benchmark Suite
• biggy: An Implementation of Unified Framework for Big Data Management System
• Tools for Unbinned Unfolding
• Towards asteroseismology of neutron stars with physics-informed neural networks
• Detection of Alzheimers Disease from MRI using Convolutional Neural Networks, Exploring Transfer Learning And BellCNN
• End-to-end losses based on speaker basis vectors and all-speaker hard negative mining for speaker verification
• AIPerf: Automated machine learning as an AI-HPC benchmark
• MOGNET: A Mux-residual quantized Network leveraging Online-Generated weights
• Trust-Region Algorithms for Training Responses: Machine Learning Methods Using Indefinite Hessian Approximations
• A Package for the Automated Classification of Images Containing Supernova Light Echoes
• Predicting Ground-Level Scene Layout from Aerial Imagery
• Towards Head Motion Compensation Using Multi-Scale Convolutional Neural Networks
• On the Exploitation of Neuroevolutionary Information: Analyzing the Past for a More Efficient Future
• Learning to Fuse Local Geometric Features for 3D Rigid Data Matching
• A Self-supervised Approach for Semantic Indexing in the Context of COVID-19 Pandemic
• Neurodevelopmental Age Estimation of Infants Using a 3D-Convolutional Neural Network Model based on Fusion MRI Sequences
• Towards Deep Representation Learning with Genetic Programming
• Deep Asymmetric Multi-task Feature Learning
• Pointwise visual field estimation from optical coherence tomography in glaucoma: a structure-function analysis using deep learning
• Highly Accelerated Multishot EPI through Synergistic Machine Learning and Joint Reconstruction
• Learning Universal Sentence Representations with Mean-Max Attention Autoencoder
• Score-Based Change Detection for Gradient-Based Learning Machines
• EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch
• Drug-drug Interaction Extraction via Recurrent Neural Network with Multiple Attention Layers
• Recurrent Estimation of Distributions
• Retrosynthetic reaction prediction using neural sequence-to-sequence models
• End-to-end Speech Recognition with Adaptive Computation Steps
• Additive manufacturing process design with differentiable simulations
• Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks
• Orthogonal and Idempotent Transformations for Learning Deep Neural Networks
• Sensing Urban Land-Use Patterns By Integrating Google Tensorflow And Scene-Classification Models
• TraceCaps: A Capsule-based Neural Network for Semantic Segmentation
• A Convolutional Neural Network-based Approach to Field Reconstruction
• Optimal Reservoir Operations using Long Short-Term Memory Network
• Closing the loop between neural network simulators and the OpenAI Gym
• Deep learning in physics: a study of dielectric quasi-cubic particles in a uniform electric field
• Facial Age Estimation using Convolutional Neural Networks
• Abductive functional programming, a semantic approach
• Teaching a GAN What Not to Learn
• Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition
• PlinyCompute: A Platform for High-Performance, Distributed, Data-Intensive Tool Development
• A generic and fast C++ optimization framework
• Gene expression modelling across multiple cell-lines with MapReduce
• Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix
• Short-time deep-learning based source separation for speech enhancement in reverberant environments with beamforming
• You Never Cluster Alone
• Correlation Propagation Networks for Scene Text Detection
• Discriminative Cross-View Binary Representation Learning
• Hair Segmentation on Time-of-Flight RGBD Images
• Simulating dysarthric speech for training data augmentation in clinical speech applications
• Analysis of memory in LSTM-RNNs for source separation
• A Partial Regularization Method for Network Compression
• Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D U-Net
• Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems
• 4-Connected Shift Residual Networks
• A Statistical Learning Approach to Reactive Power Control in Distribution Systems
• Cross-Scale Residual Network for Multiple Tasks:Image Super-resolution, Denoising, and Deblocking
• Efficient bifurcation and parameterization of multi-dimensional combustion manifolds using deep mixture of experts: an a priori study
• An Improving Framework of regularization for Network Compression
• An Improved Deep Neural Network for Modeling Speaker Characteristics at Different Temporal Scales
• Gaussian speaker embedding learning for text-independent speaker verification
• DAC: Data-free Automatic Acceleration of Convolutional Networks
• Unsupervised monocular stereo matching
• Residual-CNDS for Grand Challenge Scene Dataset
• Optimal and Fast Real-time Resources Slicing with Deep Dueling Neural Networks
• Domain-Constrained Advertising Keyword Generation
• Image-Based Geo-Localization Using Satellite Imagery
• Show, Translate and Tell
• Deep Neural Network Embeddings with Gating Mechanisms for Text-Independent Speaker Verification
• Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks
• Forget the Learning Rate, Decay Loss
• Leveraging Deep Learning to Improve the Performance Predictability of Cloud Microservices
• Static Activation Function Normalization
• Monocular Depth Estimation with Directional Consistency by Deep Networks
• Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
• Online Filter Clustering and Pruning for Efficient Convnets
• Learning Longer-term Dependencies via Grouped Distributor Unit
• Mixture separability loss in a deep convolutional network for image classification
• ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation
• Short-term Electric Load Forecasting Using TensorFlow and Deep Auto-Encoders
• The Compressed Model of Residual CNDS
• Dex: Incremental Learning for Complex Environments in Deep Reinforcement Learning
• Reduced Electron Exposure for Energy-Dispersive Spectroscopy using Dynamic Sampling
• Automatic Question-Answering Using A Deep Similarity Neural Network
• Determining Positive Cancer Rescue Mutations in p53 Based Cancers by using Artificial Intelligence
• Patterns versus Characters in Subword-aware Neural Language Modeling
• Learning to Label Affordances from Simulated and Real Data
• Deconvolution of the High Energy Particle Physics Data with Machine Learning
• A Novel Approach to Artistic Textual Visualization via GAN
• GitGraph - Architecture Search Space Creation through Frequent Computational Subgraph Mining
• Seer: Empowering Software Defined Networking with Data Analytics
• Flexible Scheduling of Distributed Analytic Applications
• Dihedral angle prediction using generative adversarial networks
• A Deep Error Correction Network for Compressed Sensing MRI
• Robust Dual View Deep Agent
• Trace your sources in large-scale data: one ring to find them all
• End-to-end Graph-based TAG Parsing with Neural Networks
• Approximate Random Dropout
• Classification of Protein Crystallization X-Ray Images Using Major Convolutional Neural Network Architectures
• A Dynamic Neural Network Approach to Generating Robot's Novel Actions: A Simulation Experiment
• End to End Brain Fiber Orientation Estimation using Deep Learning
• In situ TensorView: In situ Visualization of Convolutional Neural Networks
• Bené: On Demand Cost-Effective Scaling at the Edge
• Imagining the Unseen: Learning a Distribution over Incomplete Images with Dense Latent Trees
• Multi-scenario deep learning for multi-speaker source separation
• Towards Machine Learning-Based Optimal HAS
• Improved Deep Hashing with Soft Pairwise Similarity for Multi-label Image Retrieval
• Stereo Computation for a Single Mixture Image
• Deep Room Recognition Using Inaudible Echos
• Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems
• Learning short-term past as predictor of human behavior in commercial buildings
• Accelerate CU Partition in HEVC using Large-Scale Convolutional Neural Network
• Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment
• Practical Implementation of Memristor-Based Threshold Logic Gates
• Exploring the Vision Processing Unit as Co-processor for Inference
• A Blended Deep Learning Approach for Predicting User Intended Actions
• Deep neural network based i-vector mapping for speaker verification using short utterances
• Novel Approaches to Accelerating the Convergence Rate of Markov Decision Process for Search Result Diversification
• Scalable Deep $k$-Subspace Clustering
• Performance Estimation of Synthesis Flows cross Technologies using LSTMs and Transfer Learning
• Substation Signal Matching with a Bagged Token Classifier
• Exploiting Sentence Embedding for Medical Question Answering
• Localisation via Deep Imagination: learn the features not the map
• Affinity Derivation and Graph Merge for Instance Segmentation
• Medical Image Super-Resolution Using a Generative Adversarial Network
• On Motion Control and Machine Learning for Robotic Assembly
• A Framework for Model Search Across Multiple Machine Learning Implementations
• HRFA: High-Resolution Feature-based Attack
• DSSLP: A Distributed Framework for Semi-supervised Link Prediction
• Deep Neural Network Learning with Second-Order Optimizers -- a Practical Study with a Stochastic Quasi-Gauss-Newton Method
• Diagnosis and Analysis of Celiac Disease and Environmental Enteropathy on Biopsy Images using Deep Learning Approaches
• Sequential Routing Framework: Fully Capsule Network-based Speech Recognition
• Efficient Reinforcement Learning Development with RLzoo
• Multi-task Metric Learning for Text-independent Speaker Verification
• Adaptive Recurrent Neural Network Based on Mixture Layer
• Extraction of Discrete Spectra Modes from Video Data Using a Deep Convolutional Koopman Network
• A Novel ANN Structure for Image Recognition
• How to Train your Quadrotor: A Framework for Consistently Smooth and Responsive Flight Control via Reinforcement Learning
• COVID19-HPSMP: COVID-19 Adopted Hybrid and Parallel Deep Information Fusion Framework for Stock Price Movement Prediction
• Generation and Simulation of Yeast Microscopy Imagery with Deep Learning
• Surrogate Model Based Hyperparameter Tuning for Deep Learning with SPOT
• mil-benchmarks: Standardized Evaluation of Deep Multiple-Instance Learning Techniques
• Top squark signal significance enhancement by different Machine Learning Algorithms
• Site-Agnostic 3D Dose Distribution Prediction with Deep Learning Neural Networks
• Towards Explainable Fact Checking
• clcNet: Improving the Efficiency of Convolutional Neural Network using Channel Local Convolutions
• Where's Swimmy?: Mining unique color features buried in galaxies by deep anomaly detection using Subaru Hyper Suprime-Cam data
• Effects of Multi-Aspect Online Reviews with Unobserved Confounders: Estimation and Implication
• Learning Pruned Structure and Weights Simultaneously from Scratch: an Attention based Approach
• Classification of animal sounds in a hyperdiverse rainforest using Convolutional Neural Networks
• A Supervised Learning Framework for Joint Angle-of-Arrival and Source Number Estimation
• Subspace Graph Physics: Real-Time Rigid Body-Driven Granular Flow Simulation
• Event-level variables for semivisible jets using anomalous jet tagging
• LossPlot: A Better Way to Visualize Loss Landscapes
• ViSTRA3: Video Coding with Deep Parameter Adaptation and Post Processing
• MRI-based Surgical Planning for Lumbar Spinal Stenosis
• Vertex finding in neutrino-nucleus interaction: A Model Architecture Comparison
• GL-BLSTM: a novel structure of bidirectional long-short term memory for disulfide bonding state prediction
• Closed loop BCI System for Cybathlon 2020
• Joint cortical registration of geometry and function using semi-supervised learning
• The Relative Gaussian Mechanism and its Application to Private Gradient Descent
• Accelerating Ensemble Error Bar Prediction with Single Models Fits
• An Open-Source Framework for Efficient Numerically-Tailored Computations
• Energy Reconstruction of Non-fiducial Electron-Positron Events in the DAMPE Experiment Using Convolutional Neural Networks
• Floating-Point Neural Networks Are Provably Robust Universal Approximators
• Automated dermatoscopic pattern discovery by clustering neural network output for human-computer interaction
• Will there be a construction? Predicting road constructions based on heterogeneous spatiotemporal data
• Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services
• PDPGD: Primal-Dual Proximal Gradient Descent Adversarial Attack
• Comparison of Graphcore IPUs and Nvidia GPUsfor cosmology applications
• Adaptive Latent Space Tuning for Non-Stationary Distributions
• Anomaly Detection in Video Sequences: A Benchmark and Computational Model
• Group-Structured Adversarial Training
• Analysis of training and seed bias in small molecules generated with a conditional graph-based variational autoencoder -- Insights for practical AI-driven molecule generation
• R2F: A Remote Retraining Framework for AIoT Processors with Computing Errors
• Deep equal risk pricing of financial derivatives with non-translation invariant risk measures
• Machine Learning for Performance Prediction of Spark Cloud Applications
• Turning old models fashion again: Recycling classical CNN networks using the Lattice Transformation
• Optimizing Neural Network for Computer Vision task in Edge Device
• Quantized Variational Inference
• Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian
• Deep Learning Framework From Scratch Using Numpy
• Transformer Guided Geometry Model for Flow-Based Unsupervised Visual Odometry
• Cross-Domain Latent Modulation for Variational Transfer Learning
• TensorX: Extensible API for Neural Network Model Design and Deployment
• SOAR: A Synthesis Approach for Data Science API Refactoring
• Local Convergence of Adaptive Gradient Descent Optimizers
• Weakly-supervised multi-class object localization using only object counts as labels
• A deep perceptual metric for 3D point clouds
• On-lattice voxelated convolutional neural networks for prediction of phase diagrams and diffusion barriers in cubic alloys
• Meta-Learning with Variational Bayes
• CalibDNN: Multimodal Sensor Calibration for Perception Using Deep Neural Networks
• A Probabilistic Assessment of the COVID-19 Lockdown on Air Quality in the UK
• Convolutional Neural Networks for Real-Time Localization and Classification in Feedback Digital Microscopy
• Detect Language of Transliterated Texts
• An Integrated Enhancement Solution for 24-hour Colorful Imaging
• Goal Recognition over Imperfect Domain Models
• Deploying Scientific AI Networks at Petaflop Scale on Secure Large Scale HPC Production Systems with Containers
• Development and Validation of a Novel Prognostic Model for Predicting AMD Progression Using Longitudinal Fundus Images
• Learning from Data to Speed-up Sorted Table Search Procedures: Methodology and Practical Guidelines
• A Class of Temporal Hierarchical Exponential Random Graph Models for Longitudinal Network Data
• An Inter- and Intra-Band Loss for Pansharpening Convolutional Neural Networks
• Sparse Coding Driven Deep Decision Tree Ensembles for Nuclear Segmentation in Digital Pathology Images