TensorFlow: A system for large-scale machine learning

Abstract

TensorFlow is a machine learning system that operates at large scale and in heterogeneous environments. TensorFlow uses dataflow graphs to represent computation, shared state, and the operations that mutate that state. It maps the nodes of a dataflow graph across many machines in a cluster, and within a machine across multiple computational devices, including multicore CPUs, general-purpose GPUs, and custom designed ASICs known as Tensor Processing Units (TPUs). This architecture gives flexibility to the application developer: whereas in previous "parameter server" designs the management of shared state is built into the system, TensorFlow enables developers to experiment with novel optimizations and training algorithms. TensorFlow supports a variety of applications, with particularly strong support for training and inference on deep neural networks. Several Google services use TensorFlow in production, we have released it as an open-source project, and it has become widely used for machine learning research. In this paper, we describe the TensorFlow dataflow model in contrast to existing systems, and demonstrate the compelling performance that TensorFlow achieves for several real-world applications.

18 pages, 9 figures; v2 has a spelling correction in the metadata

References in corpus (19)

• Efficient Estimation of Word Representations in Vector Space
• Sequence to Sequence Learning with Neural Networks
• Deep Residual Learning for Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Going Deeper with Convolutions
• HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
• cuDNN: Efficient Primitives for Deep Learning
• One weird trick for parallelizing convolutional neural networks
• Exploring the Limits of Language Modeling
• Multiple Object Recognition with Visual Attention
• Revisiting Distributed Synchronous SGD
• Rethinking the Inception Architecture for Computer Vision
• Grammar as a Foreign Language
• Massively Parallel Methods for Deep Reinforcement Learning
• Document Embedding with Paragraph Vectors
• The Missing Piece in Complex Analytics: Low Latency, Scalable Model Management and Serving with Velox
• Fast Algorithms for Convolutional Neural Networks
• SparkNet: Training Deep Networks in Spark

Cited by in corpus (773)

• MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation
• On the Opportunities and Risks of Foundation Models
• Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
• DeepDTA: Deep Drug-Target Binding Affinity Prediction
• AutoML: A Survey of the State-of-the-Art
• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Open3D: A Modern Library for 3D Data Processing
• Deep Learning for Single Image Super-Resolution: A Brief Review
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Automatically designing CNN architectures using genetic algorithm for image classification
• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• Snorkel: Rapid Training Data Creation with Weak Supervision
• Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks
• Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• DeepGO: Predicting protein functions from sequence and interactions using a deep ontology-aware classifier
• Artificial Neural Networks trained through Deep Reinforcement Learning discover control strategies for active flow control
• Automatic Brain Tumor Segmentation using Cascaded Anisotropic Convolutional Neural Networks
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Neural networks for post-processing ensemble weather forecasts
• DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation
• Horovod: fast and easy distributed deep learning in TensorFlow
• FPGA-based Accelerators of Deep Learning Networks for Learning and Classification: A Review
• Recurrence is required to capture the representational dynamics of the human visual system
• Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images
• Joint entity recognition and relation extraction as a multi-head selection problem
• Weak Adversarial Networks for High-dimensional Partial Differential Equations
• Physics-informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions
• Adversarial Uncertainty Quantification in Physics-Informed Neural Networks
• SciANN: A Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
• Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges
• The Challenge of Machine Learning in Space Weather Nowcasting and Forecasting
• Real-Time Polyp Detection, Localization and Segmentation in Colonoscopy Using Deep Learning
• Artificial neural networks for neuroscientists: A primer
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Microscope 2.0: An Augmented Reality Microscope with Real-time Artificial Intelligence Integration
• MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images
• CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization
• Enhancing Clinical Concept Extraction with Contextual Embeddings
• A Survey on Edge Computing Systems and Tools
• Automatic Classification of Cancerous Tissue in Laserendomicroscopy Images of the Oral Cavity using Deep Learning
• Deep Learning of Subsurface Flow via Theory-guided Neural Network
• Efficient training of physics-informed neural networks via importance sampling
• Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture
• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Anomaly Detection with Density Estimation
• NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination
• Recursive Cascaded Networks for Unsupervised Medical Image Registration
• Diagnosis of Alzheimer's Disease via Multi-modality 3D Convolutional Neural Network
• Machine Learning for Wireless Communications in the Internet of Things: A Comprehensive Survey
• Classification without labels: Learning from mixed samples in high energy physics
• SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
• An Iterative BP-CNN Architecture for Channel Decoding
• Transfer learning for time series classification
• Transformer-CNN: Fast and Reliable tool for QSAR
• Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis
• Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis
• MCUNet: Tiny Deep Learning on IoT Devices
• Compact Convolutional Neural Networks for Classification of Asynchronous Steady-state Visual Evoked Potentials
• Medical Deep Learning -- A systematic Meta-Review
• X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data
• Deep-learning Architecture for Short-term Passenger Flow Forecasting in Urban Rail Transit
• Ray: A Distributed Framework for Emerging AI Applications
• Real-time Cardiovascular MR with Spatio-temporal Artifact Suppression using Deep Learning - Proof of Concept in Congenital Heart Disease
• Machine Learning for Microcontroller-Class Hardware: A Review
• Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
• Transfer learning based multi-fidelity physics informed deep neural network
• A Physics-Guided Neural Network Framework for Elastic Plates: Comparison of Governing Equations-Based and Energy-Based Approaches
• Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning
• EmergencyNet: Efficient Aerial Image Classification for Drone-Based Emergency Monitoring Using Atrous Convolutional Feature Fusion
• Crop Yield Prediction Integrating Genotype and Weather Variables Using Deep Learning
• LSTM-MSNet: Leveraging Forecasts on Sets of Related Time Series with Multiple Seasonal Patterns
• Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation
• Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks
• MD-GAN: Multi-Discriminator Generative Adversarial Networks for Distributed Datasets
• A test case for application of convolutional neural networks to spatio-temporal climate data: Re-identifying clustered weather patterns
• Deep ConvLSTM with self-attention for human activity decoding using wearables
• Extending the Bump Hunt with Machine Learning
• Simultaneous Corn and Soybean Yield Prediction from Remote Sensing Data Using Deep Transfer Learning
• Stochastic Super-Resolution for Downscaling Time-Evolving Atmospheric Fields with a Generative Adversarial Network
• A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video
• Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse
• Domain Adversarial for Acoustic Emotion Recognition
• Machine learning with force-field inspired descriptors for materials: fast screening and mapping energy landscape
• Deep Multimodal Subspace Clustering Networks
• From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning Techniques
• Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Language Modeling with Deep Transformers
• SuperNeurons: Dynamic GPU Memory Management for Training Deep Neural Networks
• L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
• Tiny Machine Learning: Progress and Futures
• wav2letter++: The Fastest Open-source Speech Recognition System
• Chiron: Privacy-preserving Machine Learning as a Service
• OmniFold: A Method to Simultaneously Unfold All Observables
• Deep-Learning-Based Image Segmentation Integrated with Optical Microscopy for Automatically Searching for Two-Dimensional Materials
• Simulator-free Solution of High-Dimensional Stochastic Elliptic Partial Differential Equations using Deep Neural Networks
• Automatic Brain Tumor Segmentation using Convolutional Neural Networks with Test-Time Augmentation
• Using machine learning to correct model error in data assimilation and forecast applications
• High-dimensional Dense Residual Convolutional Neural Network for Light Field Reconstruction
• Graph Neural Networks Based Detection of Stealth False Data Injection Attacks in Smart Grids
• Simulation Assisted Likelihood-free Anomaly Detection
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• A Multi-Objective Deep Reinforcement Learning Framework
• A nonlocal physics-informed deep learning framework using the peridynamic differential operator
• Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials
• RSGAN: Face Swapping and Editing using Face and Hair Representation in Latent Spaces
• BigDL: A Distributed Deep Learning Framework for Big Data
• Real-Time Radar-Based Gesture Detection and Recognition Built in an Edge-Computing Platform
• UAV and Machine Learning Based Refinement of a Satellite-Driven Vegetation Index for Precision Agriculture
• Real-Time Optimal Control for Irregular Asteroid Landings Using Deep Neural Networks
• Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications
• Stereo Magnification: Learning View Synthesis using Multiplane Images
• TensorCircuit: a Quantum Software Framework for the NISQ Era
• Artificial intelligence adoption in the physical sciences, natural sciences, life sciences, social sciences and the arts and humanities: A bibliometric analysis of research publications from 1960-2021
• FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measure
• EsDNN: Deep Neural Network based Multivariate Workload Prediction Approach in Cloud Environment
• OpenFL: An open-source framework for Federated Learning
• PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
• Deep Learning-Based Model Predictive Control for Resonant Power Converters
• Deep Learning in Mobile and Wireless Networking: A Survey
• Earthquake magnitude and location estimation from real time seismic waveforms with a transformer network
• Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism
• Format Abstraction for Sparse Tensor Algebra Compilers
• Reinforced dynamics for enhanced sampling in large atomic and molecular systems
• Learning to Protect Communications with Adversarial Neural Cryptography
• Disentangling Long and Short-Term Interests for Recommendation
• A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison
• Path-Restore: Learning Network Path Selection for Image Restoration
• Flexible Clustered Federated Learning for Client-Level Data Distribution Shift
• Solving Electrical Impedance Tomography with Deep Learning
• Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models
• Robust High-dimensional Memory-augmented Neural Networks
• BaitWatcher: A lightweight web interface for the detection of incongruent news headlines
• TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank
• The Programmable Data Plane: Abstractions, Architectures, Algorithms, and Applications
• Exploring the Role of Visual Content in Fake News Detection
• DeePore: a deep learning workflow for rapid and comprehensive characterization of porous materials
• Mapping neutron star data to the equation of state using the deep neural network
• Discover Your Social Identity from What You Tweet: a Content Based Approach
• Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
• Friend, Collaborator, Student, Manager: How Design of an AI-Driven Game Level Editor Affects Creators
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• Training neural nets to learn reactive potential energy surfaces using interactive quantum chemistry in virtual reality
• GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding
• Learning to Classify from Impure Samples with High-Dimensional Data
• Review: Deep Learning in Electron Microscopy
• Pretrained Transformers for Text Ranking: BERT and Beyond
• A General Approach to Seismic Inversion with Automatic Differentiation
• Relay: A New IR for Machine Learning Frameworks
• A Rotation-Invariant Framework for Deep Point Cloud Analysis
• Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filtering
• FT-CNN: Algorithm-Based Fault Tolerance for Convolutional Neural Networks
• Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
• Short-segment heart sound classification using an ensemble of deep convolutional neural networks
• Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks
• Roundtrip: A Deep Generative Neural Density Estimator
• DeepCorn: A Semi-Supervised Deep Learning Method for High-Throughput Image-Based Corn Kernel Counting and Yield Estimation
• Learning 3D Mineral Prospectivity from 3D Geological Models Using Convolutional Neural Networks: Application to a Structure-controlled Hydrothermal Gold Deposit
• Parameter Hub: a Rack-Scale Parameter Server for Distributed Deep Neural Network Training
• Physics and Equality Constrained Artificial Neural Networks: Application to Forward and Inverse Problems with Multi-fidelity Data Fusion
• Optimized Deep Encoder-Decoder Methods for Crack Segmentation
• Fast and accurate simulation of particle detectors using generative adversarial networks
• Measurements of Higgs boson production cross sections and couplings in the diphoton decay channel at $\sqrt{s}=$ 13 TeV
• Capsule Attention for Multimodal EEG-EOG Representation Learning with Application to Driver Vigilance Estimation
• Sequential Convolutional Recurrent Neural Networks for Fast Automatic Modulation Classification
• Automated crater detection on Mars using deep learning
• Taurus: A Data Plane Architecture for Per-Packet ML
• Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusion
• Deep Learning for One-dimensional Consolidation
• A Bayesian Deep Learning Framework for End-To-End Prediction of Emotion from Heartbeat
• Physics-informed neural networks for myocardial perfusion MRI quantification
• Deep Model Predictive Control with Online Learning for Complex Physical Systems
• FEA-Net: A Physics-guided Data-driven Model for Efficient Mechanical Response Prediction
• Autoregressive Convolutional Neural Networks for Asynchronous Time Series
• An End-to-End Deep Learning Approach for Epileptic Seizure Prediction
• Deep Networks as Approximators of Optimal Transfers Solutions in Multitarget Missions
• Deep Probabilistic Programming
• A convolutional neural network approach to deblending seismic data
• A Method of Rapid Quantification of Patient-Specific Organ Dose for CT Using Coupled Deep-Learning based Multi-Organ Segmentation and GPU-accelerated Monte Carlo Dose Computing
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• Ensemble Conformalized Quantile Regression for Probabilistic Time Series Forecasting
• Deep Retinal Image Segmentation with Regularization Under Geometric Priors
• Predicting orientation-dependent plastic susceptibility from static structure in amorphous solids via deep learning
• A deep learning framework for solution and discovery in solid mechanics
• DocTer: Documentation Guided Fuzzing for Testing Deep Learning API Functions
• Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectives
• DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation
• The Materials Simulation Toolkit for Machine Learning (MAST-ML): an automated open source toolkit to accelerate data-driven materials research
• Launching Adversarial Attacks against Network Intrusion Detection Systems for IoT
• Practical Approaches Towards Deep-Learning Based Cross-Device Power Side Channel Attack
• Solving forward and inverse problems of the logarithmic nonlinear Schrodinger equation with PT-symmetric harmonic potential via deep learning
• A Survey on Geographically Distributed Big-Data Processing using MapReduce
• Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training
• Net2Vis -- A Visual Grammar for Automatically Generating Publication-Tailored CNN Architecture Visualizations
• Non-rigid image registration using fully convolutional networks with deep self-supervision
• Optimizing CNN Model Inference on CPUs
• Deep learning enables high-throughput analysis of particle-aggregation-based bio-sensors imaged using holography
• Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework
• Sensitivity Analysis of Deep Neural Networks
• Observation of Josephson Harmonics in Tunnel Junctions
• Decoupled Novel Object Captioner
• Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptation
• Methodology study of machine learning for the neutron star equation of state
• Analysis of Large-Scale Multi-Tenant GPU Clusters for DNN Training Workloads
• Photonic spiking neural networks and CMOS-compatible graphene-on-silicon spiking neurons
• Massive Exploration of Neural Machine Translation Architectures
• Learned discretizations for passive scalar advection in a 2-D turbulent flow
• The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Large
• Communication optimization strategies for distributed deep neural network training: A survey
• Bump Hunting in Latent Space
• FedSAE: A Novel Self-Adaptive Federated Learning Framework in Heterogeneous Systems
• Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
• Dynamic Facial Expression Generation on Hilbert Hypersphere with Conditional Wasserstein Generative Adversarial Nets
• Deep Signal Recovery with One-Bit Quantization
• Text Classification using Capsules
• ABCDisCo: Automating the ABCD Method with Machine Learning
• SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties
• A Survey of Breast Cancer Screening Techniques: Thermography and Electrical Impedance Tomography
• Neuroimaging Modality Fusion in Alzheimer's Classification Using Convolutional Neural Networks
• Scanner: Efficient Video Analysis at Scale
• Characterizing Deep-Learning I/O Workloads in TensorFlow
• TensorLayer: A Versatile Library for Efficient Deep Learning Development
• Learning Combinations of Activation Functions
• TSFC: a structure-preserving form compiler
• GPU Acceleration of ADMM for Large-Scale Quadratic Programming
• Queueing Network Controls via Deep Reinforcement Learning
• EDITH :ECG biometrics aided by Deep learning for reliable Individual auTHentication
• Distributed CNN Inference on Resource-Constrained UAVs for Surveillance Systems: Design and Optimization
• Edge and Identity Preserving Network for Face Super-Resolution
• FRnet-DTI: Deep Convolutional Neural Networks with Evolutionary and Structural Features for Drug-Target Interaction
• HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework
• Targeting Multi-Loop Integrals with Neural Networks
• A guide for deploying Deep Learning in LHC searches: How to achieve optimality and account for uncertainty
• Multimodal Affective States Recognition Based on Multiscale CNNs and Biologically Inspired Decision Fusion Model
• Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks
• Lightweight Modules for Efficient Deep Learning based Image Restoration
• Predicting Yield Performance of Parents in Plant Breeding: A Neural Collaborative Filtering Approach
• QFold: Quantum Walks and Deep Learning to Solve Protein Folding
• Automated Pruning for Deep Neural Network Compression
• Using Deep Learning to Extend the Range of Air-Pollution Monitoring and Forecasting
• A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation
• Multiscale Deep Equilibrium Models
• Multi-Objective Bayesian Optimization for Accelerator Tuning
• Neural Network Augmented Physics Models for Systems with Partially Unknown Dynamics: Application to Slider-Crank Mechanism
• Query Processing on Tensor Computation Runtimes
• Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets with Multi-stream Inputs
• Learning from synthetic photorealistic raindrop for single image raindrop removal
• Restructuring Batch Normalization to Accelerate CNN Training
• A Simple Differentiable Programming Language
• Semi-parametric Topological Memory for Navigation
• Graph neural network initialisation of quantum approximate optimisation
• Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications
• Geometry-Contrastive GAN for Facial Expression Transfer
• A feed-forward neural network as a nonlinear dynamics integrator for supercontinuum generation
• Block Deep Neural Network-Based Signal Detector for Generalized Spatial Modulation
• LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision
• RecSim: A Configurable Simulation Platform for Recommender Systems
• Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming
• Classification of Huntington Disease using Acoustic and Lexical Features
• MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
• Deep Learning for Computational Chemistry
• LiFT: A Scalable Framework for Measuring Fairness in ML Applications
• Deep learning based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms
• Scalable Distributed DNN Training using TensorFlow and CUDA-Aware MPI: Characterization, Designs, and Performance Evaluation
• Automatic Differentiation in PCF
• Omnivore: An Optimizer for Multi-device Deep Learning on CPUs and GPUs
• Zero-Shot Learning by Generating Pseudo Feature Representations
• End-to-End Learning for VCSEL-based Optical Interconnects: State-of-the-Art, Challenges, and Opportunities
• Equivariant Energy Flow Networks for Jet Tagging
• Image-based model parameter optimization using Model-Assisted Generative Adversarial Networks
• Accelerating hydrodynamic simulations of urban drainage systems with physics-guided machine learning
• Emotional Speaker Identification using a Novel Capsule Nets Model
• Towards Training Reproducible Deep Learning Models
• Scalable Graph Neural Network Training: The Case for Sampling
• There Are No Data Like More Data- Datasets for Deep Learning in Earth Observation
• Presenting Unbinned Differential Cross Section Results
• A framework for remote sensing images processing using deep learning technique
• Automatic classification of plasma regions in near-Earth space with supervised machine learning: application to Magnetospheric Multi Scale 2016-2019 observations
• Cross-Lingual Machine Reading Comprehension
• An Iterative Machine-Learning Framework for RANS Turbulence Modeling
• Neutrino interaction classification with a convolutional neural network in the DUNE far detector
• TensorOpt: Exploring the Tradeoffs in Distributed DNN Training with Auto-Parallelism
• Photonic convolutional neural networks using integrated diffractive optics
• PoreNet: CNN-based Pore Descriptor for High-resolution Fingerprint Recognition
• Robust Reference Frame Extraction from Unsteady 2D Vector Fields with Convolutional Neural Networks
• Learning Based User Scheduling in Reconfigurable Intelligent Surface Assisted Multiuser Downlink
• Exploring convolutional neural networks with transfer learning for diagnosing Lyme disease from skin lesion images
• Addressing Overfitting on Pointcloud Classification using Atrous XCRF
• Multi-Task Representation Learning with Multi-View Graph Convolutional Networks
• E Pluribus Unum Ex Machina: Learning from Many Collider Events at Once
• A Cost-based Optimizer for Gradient Descent Optimization
• Learning macroscopic parameters in nonlinear multiscale simulations using nonlocal multicontinua upscaling techniques
• Semi-Synchronous Federated Learning for Energy-Efficient Training and Accelerated Convergence in Cross-Silo Settings
• Video Big Data Analytics in the Cloud: A Reference Architecture, Survey, Opportunities, and Open Research Issues
• Deep Learning-Based Computer Vision for Real Time Intravenous Drip Infusion Monitoring
• Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices
• LogME: Practical Assessment of Pre-trained Models for Transfer Learning
• HP-GNN: Generating High Throughput GNN Training Implementation on CPU-FPGA Heterogeneous Platform
• Tangent Convolutions for Dense Prediction in 3D
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
• Binary Single-dimensional Convolutional Neural Network for Seizure Prediction
• Accelerating Large-Scale-Structure data analyses by emulating Boltzmann solvers and Lagrangian Perturbation Theory
• Open-Set Recognition Using Intra-Class Splitting
• Neural network setups for a precise detection of the many-body localization transition: finite-size scaling and limitations
• A Convolutional Neural Network Approach to the Classification of Engineering Models
• How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition
• Semi-Dynamic Load Balancing: Efficient Distributed Learning in Non-Dedicated Environments
• Application of Deep Learning to Sphere Decoding for Large MIMO Systems
• LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations
• Fog Computing on Constrained Devices: Paving the Way for the Future IoT
• Convolutional neural networks enable high-fidelity prediction of path-dependent diffusion barrier spectra in multi-principal element alloys
• secureTF: A Secure TensorFlow Framework
• Predicting the Time Until a Vehicle Changes the Lane Using LSTM-based Recurrent Neural Networks
• Context is Key: Grammatical Error Detection with Contextual Word Representations
• Scalable Hamiltonian learning for large-scale out-of-equilibrium quantum dynamics
• PyPose: A Library for Robot Learning with Physics-based Optimization
• A Comparison of Machine Learning Algorithms for the Surveillance of Autism Spectrum Disorder
• Kronecker Attention Networks
• TensorSCONE: A Secure TensorFlow Framework using Intel SGX
• Combining Optimal Control and Learning for Visual Navigation in Novel Environments
• A Cornucopia of AdS${}_5$ Vacua
• ModalPINN: an extension of Physics-Informed Neural Networks with enforced truncated Fourier decomposition for periodic flow reconstruction using a limited number of imperfect sensors
• Fuzzy Pooling
• OneFlow: Redesign the Distributed Deep Learning Framework from Scratch
• Declarative Recursive Computation on an RDBMS, or, Why You Should Use a Database For Distributed Machine Learning
• Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future
• Tensor Graph Convolutional Networks for Multi-relational and Robust Learning
• Training Variational Networks with Multi-Domain Simulations: Speed-of-Sound Image Reconstruction
• An Interactive Data Visualization and Analytics Tool to Evaluate Mobility and Sociability Trends During COVID-19
• ExPAN(N)D: Exploring Posits for Efficient Artificial Neural Network Design in FPGA-based Systems
• DeepWay: a Deep Learning Waypoint Estimator for Global Path Generation
• An attentive neural architecture for joint segmentation and parsing and its application to real estate ads
• SymmetryGAN: Symmetry Discovery with Deep Learning
• Meta-learning Pseudo-differential Operators with Deep Neural Networks
• Predicting nonlinear dynamics of optical solitons in optical fiber via the SCPINN
• Binary Neutron Stars Gravitational Wave Detection Based on Wavelet Packet Analysis And Convolutional Neural Networks
• Seismic Inversion by Hybrid Machine Learning
• ZMCintegral: a Package for Multi-Dimensional Monte Carlo Integration on Multi-GPUs
• An Efficient Statistical-based Gradient Compression Technique for Distributed Training Systems
• Automatic Three-Dimensional Cephalometric Annotation System Using Three-Dimensional Convolutional Neural Networks
• Kidney tumor segmentation using an ensembling multi-stage deep learning approach. A contribution to the KiTS19 challenge
• Merlin HugeCTR: GPU-accelerated Recommender System Training and Inference
• Graph CNN for Moving Object Detection in Complex Environments from Unseen Videos
• Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions
• Extracting Urban Sound Information for Residential Areas in Smart Cities Using an End-to-End IoT System
• CA-GAN: Weakly Supervised Color Aware GAN for Controllable Makeup Transfer
• Fog Intelligence for Network Anomaly Detection
• Noise2Context: Context-assisted Learning 3D Thin-layer Low Dose CT Without Clean Data
• Amobee at SemEval-2018 Task 1: GRU Neural Network with a CNN Attention Mechanism for Sentiment Classification
• Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles with Label Propagation for Cross-Domain Adaptation
• Machine Learning Approaches to Learn HyChem Models
• dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python
• Information Aware Max-Norm Dirichlet Networks for Predictive Uncertainty Estimation
• Correlation Net: Spatiotemporal multimodal deep learning for action recognition
• Relation-Based Associative Joint Location for Human Pose Estimation in Videos
• Identification of MIMO Wiener-type Koopman Models for Data-Driven Model Reduction using Deep Learning
• Quantum Capsule Networks
• Constellation Design for Deep Joint Source-Channel Coding
• New methods of removing debris and high-throughput counting of cyst nematode eggs extracted from field soil
• Comparative Analysis of Open Source Frameworks for Machine Learning with Use Case in Single-Threaded and Multi-Threaded Modes
• Sketch-Guided Scenery Image Outpainting
• Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps
• FedAT: A High-Performance and Communication-Efficient Federated Learning System with Asynchronous Tiers
• Implementing graph neural networks with TensorFlow-Keras
• Unsupervised Seismic Footprint Removal With Physical Prior Augmented Deep Autoencoder
• SPRING: A Sparsity-Aware Reduced-Precision Monolithic 3D CNN Accelerator Architecture for Training and Inference
• High-Dimensional Feature Selection for Genomic Datasets
• Universal programmable photonic architecture for quantum information processing
• Efficient Implementation of Non-linear Flow Law Using Neural Network into the Abaqus Explicit FEM code
• Confusion2Vec: Towards Enriching Vector Space Word Representations with Representational Ambiguities
• ACETest: Automated Constraint Extraction for Testing Deep Learning Operators
• Automated discovery of GPCR bioactive ligands
• Fast meningioma segmentation in T1-weighted MRI volumes using a lightweight 3D deep learning architecture
• Deep Reinforcement Learning-based Content Migration for Edge Content Delivery Networks with Vehicular Nodes
• Pure Tensor Program Rewriting via Access Patterns (Representation Pearl)
• A new scalable algorithm for computational optimal control under uncertainty
• LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection
• DEMC: A Deep Dual-Encoder Network for Denoising Monte Carlo Rendering
• DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias
• Unveiling new disease, pathway, and gene associations via multi-scale neural networks
• Hierarchically modelling Kepler dwarfs and subgiants to improve inference of stellar properties with asteroseismology
• Random Error Sampling-based Recurrent Neural Network Architecture Optimization
• Learning and Transferring IDs Representation in E-commerce
• A Light Dual-Task Neural Network for Haze Removal
• PyRCN: A Toolbox for Exploration and Application of Reservoir Computing Networks
• HongTu: Scalable Full-Graph GNN Training on Multiple GPUs (via communication-optimized CPU data offloading)
• Evolutionary Quantum Architecture Search for Parametrized Quantum Circuits
• Physics-informed neural networks modeling for systems with moving immersed boundaries: application to an unsteady flow past a plunging foil
• Bayesian Neural Architecture Search using A Training-Free Performance Metric
• A DICOM Framework for Machine Learning Pipelines against Real-Time Radiology Images
• Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals
• Guardians of the Deep Fog: Failure-Resilient DNN Inference from Edge to Cloud
• DL2: A Deep Learning-driven Scheduler for Deep Learning Clusters
• Exact constraints and appropriate norms in machine learned exchange-correlation functionals
• SRL-SOA: Self-Representation Learning with Sparse 1D-Operational Autoencoder for Hyperspectral Image Band Selection
• DiffPrep: Differentiable Data Preprocessing Pipeline Search for Learning over Tabular Data
• Deradicalizing YouTube: Characterization, Detection, and Personalization of Religiously Intolerant Arabic Videos
• Russian-German Astroparticle Data Life Cycle Initiative
• LBCF: A Large-Scale Budget-Constrained Causal Forest Algorithm
• Unbinned Deep Learning Jet Substructure Measurement in High $Q^2$ ep collisions at HERA
• Distilled Neural Networks for Efficient Learning to Rank
• Integration of Leaky-Integrate-and-Fire-Neurons in Deep Learning Architectures
• Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers
• Deep learning techniques applied to the physics of extensive air showers
• A0C: Alpha Zero in Continuous Action Space
• Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching
• Hybrid Digital Twin for process industry using Apros simulation environment
• RealFormer: Transformer Likes Residual Attention
• Referenceless characterisation of complex media using physics-informed neural networks
• A Transfer Learning Framework for Anomaly Detection Using Model of Normality
• Comparing Machine Learning and Interpolation Methods for Loop-Level Calculations
• S3: A Spectral-Spatial Structure Loss for Pan-Sharpening Networks
• Fourier Neural Networks: A Comparative Study
• Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
• tf-Darshan: Understanding Fine-grained I/O Performance in Machine Learning Workloads
• QA4IE: A Question Answering based Framework for Information Extraction
• There is Limited Correlation between Coverage and Robustness for Deep Neural Networks
• A Neural-Network Framework for the Design of Individualised Hearing-Loss Compensation
• Scalable Causal Structure Learning: Scoping Review of Traditional and Deep Learning Algorithms and New Opportunities in Biomedicine
• Implicit Dimension Identification in User-Generated Text with LSTM Networks
• Fusion: Efficient and Secure Inference Resilient to Malicious Servers
• Accuracy-Efficiency Trade-Offs and Accountability in Distributed ML Systems
• Efficient Pipeline Planning for Expedited Distributed DNN Training
• A stacked deep convolutional neural network to predict the remaining useful life of a turbofan engine
• Weakly-supervised Contextualization of Knowledge Graph Facts
• Combining Adversarial Training and Disentangled Speech Representation for Robust Zero-Resource Subword Modeling
• Dynamic Parameter Allocation in Parameter Servers
• Fast On-the-fly Retraining-free Sparsification of Convolutional Neural Networks
• MXNET-MPI: Embedding MPI parallelism in Parameter Server Task Model for scaling Deep Learning
• Spatio-temporal Multi-task Learning for Cardiac MRI Left Ventricle Quantification
• Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping
• Blending gradient boosted trees and neural networks for point and probabilistic forecasting of hierarchical time series
• TensorFlow Estimators: Managing Simplicity vs. Flexibility in High-Level Machine Learning Frameworks
• Discriminative Sentence Modeling for Story Ending Prediction
• Lightweight and Efficient Neural Natural Language Processing with Quaternion Networks
• Behavior Self-Organization Supports Task Inference for Continual Robot Learning
• Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation
• Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events
• Adversarial Infidelity Learning for Model Interpretation
• QuickSkill: Novice Skill Estimation in Online Multiplayer Games
• Technical Considerations for Semantic Segmentation in MRI using Convolutional Neural Networks
• Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
• Efficient Misalignment-Robust Multi-Focus Microscopical Images Fusion
• Backprop with Approximate Activations for Memory-efficient Network Training
• PyLightcurve-torch: a transit modelling package for deep learning applications in PyTorch
• Image features of a splashing drop on a solid surface extracted using a feedforward neural network
• Consistent and symmetry preserving data-driven interface reconstruction for the level-set method
• WearMask: Fast In-browser Face Mask Detection with Serverless Edge Computing for COVID-19
• Can We Leverage Predictive Uncertainty to Detect Dataset Shift and Adversarial Examples in Android Malware Detection?
• Quantum State Tomography with Conditional Generative Adversarial Networks
• EvoAAA: An evolutionary methodology for automated \neural autoencoder architecture search
• Deep Gaussian Process-Based Bayesian Inference for Contaminant Source Localization
• Fast and Accurate 3D Hand Pose Estimation via Recurrent Neural Network for Capturing Hand Articulations
• A Convolutional LSTM based Residual Network for Deepfake Video Detection
• An embarrassingly simple approach to neural multiple instance classification
• A General Machine Learning-based Approach for Inverse Design of One-dimensional Photonic Crystals Toward Targeted Visible Light Reflection Spectrum
• A scalable saliency-based Feature selection method with instance level information
• Unsupervised Learning of Shape and Pose with Differentiable Point Clouds
• Parameter Estimation using Neural Networks in the Presence of Detector Effects
• Time-dependent atomic magnetometry with a recurrent neural network
• Point Cloud-based Proactive Link Quality Prediction for Millimeter-wave Communications
• Nigraha: Machine-learning based pipeline to identify and evaluate planet candidates from TESS
• Decentralized Learning Made Easy with DecentralizePy
• Real-Time Machine Learning: The Missing Pieces
• EigenRank by Committee: A Data Subset Selection and Failure Prediction paradigm for Robust Deep Learning based Medical Image Segmentation
• DNNFusion: Accelerating Deep Neural Networks Execution with Advanced Operator Fusion
• Efficiency in the Serverless Cloud Paradigm: A Survey on the Reusing and Approximation Aspects
• POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
• Nonlinear Dimensionality Reduction for Data Visualization: An Unsupervised Fuzzy Rule-based Approach
• Automatic classification of eclipsing binary stars using deep learning methods
• Enabling Large Batch Size Training for DNN Models Beyond the Memory Limit While Maintaining Performance
• EEG-based Texture Roughness Classification in Active Tactile Exploration with Invariant Representation Learning Networks
• Elvet -- a neural network-based differential equation and variational problem solver
• Robust deep learning for emulating turbulent viscosities
• Improving Search with Supervised Learning in Trick-Based Card Games
• A Secure Mobile Authentication Alternative to Biometrics
• Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval
• Exploiting stance hierarchies for cost-sensitive stance detection of Web documents
• QPyTorch: A Low-Precision Arithmetic Simulation Framework
• Scheduling Computation Graphs of Deep Learning Models on Manycore CPUs
• Towards Understanding the Faults of JavaScript-Based Deep Learning Systems
• Deep Reinforcement Learning Designed Shinnar-Le Roux RF Pulse using Root-Flipping: DeepRF_SLR
• Adversarial System Variant Approximation to Quantify Process Model Generalization
• Improved Multi-Scale Grid Rendering of Point Clouds for Radar Object Detection Networks
• Capsule networks with non-iterative cluster routing
• A Robot to Shape your Natural Plant: The Machine Learning Approach to Model and Control Bio-Hybrid Systems
• A New Ensemble Learning Framework for 3D Biomedical Image Segmentation
• Polynomial methods in statistical inference: theory and practice
• Domain-specific Communication Optimization for Distributed DNN Training
• Spatial Language Representation with Multi-Level Geocoding
• Optimizing Task Placement and Online Scheduling for Distributed GNN Training Acceleration
• Joint Spatial and Angular Super-Resolution from a Single Image
• Lightweight and Efficient Image Super-Resolution with Block State-based Recursive Network
• Classification and reconstruction of optical quantum states with deep neural networks
• Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback
• Portable, high-performance containers for HPC
• Low-Cost Recurrent Neural Network Expected Performance Evaluation
• Energy spectra of elemental groups of cosmic rays with the KASCADE experiment data and machine learning
• Enhancing the hunt for new phenomena in dijet final-states using anomaly detection filters at the High-Luminosity Large Hadron Collider
• Prototype of deployment of Federated Learning with IoT devices
• An End-to-End Approach to Natural Language Object Retrieval via Context-Aware Deep Reinforcement Learning
• Android Malware Detection using Large-scale Network Representation Learning
• Magnetic Resonance Fingerprinting Reconstruction Using Recurrent Neural Networks
• ZMCintegral-v5: Support for Integrations with the Scanning of Large Parameter Grids on Multi-GPUs
• A Deep Learning-Based Approach for Cell Outage Compensation in NOMA Networks
• Separation of track- and shower-like energy deposits in ProtoDUNE-SP using a convolutional neural network
• ModelHub: Towards Unified Data and Lifecycle Management for Deep Learning
• CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
• Primer: Searching for Efficient Transformers for Language Modeling
• DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
• Gradient-guided Loss Masking for Neural Machine Translation
• Learning to infer: RL-based search for DNN primitive selection on Heterogeneous Embedded Systems
• Scale-Invariant Structure Saliency Selection for Fast Image Fusion
• Unsupervised High-Resolution Depth Learning From Videos With Dual Networks
• Compositional Generalization for Primitive Substitutions
• A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models
• A Survey on Parallelism and Determinism
• Decoding the Rejuvenating Effects of Mechanical Loading on Skeletal Maturation using in Vivo Imaging and Deep Learning
• Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models
• Emerging Directions in Geophysical Inversion
• One-Class Feature Learning Using Intra-Class Splitting
• HAFLO: GPU-Based Acceleration for Federated Logistic Regression
• C^3Net: End-to-End deep learning for efficient real-time visual active camera control
• Exploring the limits of Concurrency in ML Training on Google TPUs
• KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks
• Learning Generalized Quasi-Geostrophic Models Using Deep Neural Numerical Models
• Feature-weighted Stacking for Nonseasonal Time Series Forecasts: A Case Study of the COVID-19 Epidemic Curves
• Higher Order Automatic Differentiation of Higher Order Functions
• Memory Optimization for Deep Networks
• Multi-turn Inference Matching Network for Natural Language Inference
• Search for light long-lived particles decaying to displaced jets in proton-proton collisions at $\sqrt{s}$ = 13.6 TeV
• Node-Based Job Scheduling for Large Scale Simulations of Short Running Jobs
• Improving the Expressiveness of Deep Learning Frameworks with Recursion
• LCEval: Learned Composite Metric for Caption Evaluation
• Augmenting semantic lexicons using word embeddings and transfer learning
• Learning Convex Optimization Control Policies
• Im2win: Memory Efficient Convolution On SIMD Architectures
• PhotoSafer: Content-Based and Context-Aware Private Photo Protection for Smartphones
• Denotational Correctness of Forward-Mode Automatic Differentiation for Iteration and Recursion
• Federated Transfer Learning with Dynamic Gradient Aggregation
• Deep Probabilistic Programming Languages: A Qualitative Study
• Accelerating Deep Neural Networks for Real-time Data Selection for High-resolution Imaging Particle Detectors
• A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics
• Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers
• Physics-informed active learning with simultaneous weak-form latent space dynamics identification
• Learning Versatile Convolution Filters for Efficient Visual Recognition
• Towards Neural Decompilation
• Session-based Social and Dependency-aware Software Recommendation
• Challenges in Migrating Imperative Deep Learning Programs to Graph Execution: An Empirical Study
• Deep-Edge: An Efficient Framework for Deep Learning Model Update on Heterogeneous Edge
• ER-AE: Differentially Private Text Generation for Authorship Anonymization
• Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies
• Detection of Paroxysmal Atrial Fibrillation using Attention-based Bidirectional Recurrent Neural Networks
• VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles
• Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
• Physically Explainable Deep Learning for Convective Initiation Nowcasting Using GOES-16 Satellite Observations
• Software defined demodulation of multiple frequency shift keying with dense neural network for weak signal communications
• Stochastic Gradient Descent on Highly-Parallel Architectures
• Convolutional Neural Networks Quantization with Attention
• Towards cost-effective and resource-aware aggregation at Edge for Federated Learning
• An edge-based architecture to support the execution of ambience intelligence tasks using the IoP paradigm
• GapPredict: A Language Model for Resolving Gaps in Draft Genome Assemblies
• LAMPRET: Layout-Aware Multimodal PreTraining for Document Understanding
• Prediction of the morphological evolution of a splashing drop using an encoder-decoder
• Fully-Convolutional Intensive Feature Flow Neural Network for Text Recognition
• Unbiased Pairwise Learning from Implicit Feedback for Recommender Systems without Biased Variance Control
• Blind Deinterleaving of Signals in Time Series with Self-attention Based Soft Min-cost Flow Learning
• Gauntlet: Finding Bugs in Compilers for Programmable Packet Processing
• Workflow environments for advanced cyberinfrastructure platforms
• Light Stage Super-Resolution: Continuous High-Frequency Relighting
• Variational Leakage: The Role of Information Complexity in Privacy Leakage
• LazyTensor: combining eager execution with domain-specific compilers
• GPU-based Self-Organizing Maps for Post-Labeled Few-Shot Unsupervised Learning
• Volterra Neural Networks (VNNs)
• Low-latency job scheduling with preemption for the development of deep learning
• Accurate Prediction of Bonding Properties by A Machine Learning-based Model using Isolated States Before Bonding
• MaLTESE: Large-Scale Simulation-Driven Machine Learning for Transient Driving Cycles
• GRAPHOPT: constrained-optimization-based parallelization of irregular graphs
• ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
• Recognising Cardiac Abnormalities in Wearable Device Photoplethysmography (PPG) with Deep Learning
• RNNoise-Ex: Hybrid Speech Enhancement System based on RNN and Spectral Features
• Layer-wise Relevance Propagation for Explainable Recommendations
• Ed-Fed: A generic federated learning framework with resource-aware client selection for edge devices
• SQLFlow: A Bridge between SQL and Machine Learning
• Ordering Chaos: Memory-Aware Scheduling of Irregularly Wired Neural Networks for Edge Devices
• Chest X-ray Inpainting with Deep Generative Models
• Deeply Learned Preselection of Higgs Dijet Decays at Future Lepton Colliders
• From Domain-Specific Languages to Memory-Optimized Accelerators for Fluid Dynamics
• Delay-Constrained Rate Control for Real-Time Video Streaming with Bounded Neural Network
• A deep learning approach to multi-track location and orientation in gaseous drift chambers
• sbp-env: Sampling-based Motion Planners' Testing Environment
• Discourse-Wizard: Discovering Deep Discourse Structure in your Conversation with RNNs
• Optimizing DNN Compilation for Distributed Training with Joint OP and Tensor Fusion
• Block Shuffle: A Method for High-resolution Fast Style Transfer with Limited Memory
• Influence of Apophis' spin axis variations on a spacecraft during the 2029 close approach with Earth
• Efficient CHAD
• On Optimizing Operator Fusion Plans for Large-Scale Machine Learning in SystemML
• The Three Pillars of Machine Programming
• The CoRa Tensor Compiler: Compilation for Ragged Tensors with Minimal Padding
• i-Razor: A Differentiable Neural Input Razor for Feature Selection and Dimension Search in DNN-Based Recommender Systems
• pPython for Parallel Python Programming
• Towards Linear Algebra over Normalized Data
• Identifying Risk of Opioid Use Disorder for Patients Taking Opioid Medications with Deep Learning
• A 1000-fold Acceleration of Hidden Markov Model Fitting using Graphical Processing Units, with application to Nonvolcanic Tremor Classification
• EM-X-DL: Efficient Cross-Device Deep Learning Side-Channel Attack with Noisy EM Signatures
• GENNAPE: Towards Generalized Neural Architecture Performance Estimators
• Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks
• ACORNS: An Easy-To-Use Code Generator for Gradients and Hessians
• Stock price prediction using BERT and GAN
• Approximating the Hotelling Observer with Autoencoder-Learned Efficient Channels for Binary Signal Detection Tasks
• Towards scalable pattern-based optimization for dense linear algebra
• Improving Parametric Neural Networks for High-Energy Physics (and Beyond)
• A Neural Solver for Variational Problems on CAD Geometries with Application to Electric Machine Simulation
• TryOnGAN: Body-Aware Try-On via Layered Interpolation
• RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition
• Towards a Machine-Learned Poisson Solver for Low-Temperature Plasma Simulations in Complex Geometries
• Immigration Document Classification and Automated Response Generation
• Track finding with deep neural networks
• Surrogate models for lightcurves and photosphere properties of Type II supernovae
• Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
• Unsupervised Learning of KB Queries in Task-Oriented Dialogs
• Transactional Python for Durable Machine Learning: Vision, Challenges, and Feasibility
• A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19
• Genetic Neural Architecture Search for automatic assessment of human sperm images
• Automated Rib Fracture Detection of Postmortem Computed Tomography Images Using Machine Learning Techniques
• Unsupervised Detection of Distinctive Regions on 3D Shapes
• CLAASIC: a Cortex-Inspired Hardware Accelerator
• Deep Fundamental Factor Models
• To Relieve Your Headache of Training an MRF, Take AdVIL
• Imitation-Based Active Camera Control with Deep Convolutional Neural Network
• OpenHPS: An Open Source Hybrid Positioning System
• Dynamic Automatic Differentiation of GPU Broadcast Kernels
• Multi-View Frame Reconstruction with Conditional GAN
• Learning to Read by Spelling: Towards Unsupervised Text Recognition
• A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks
• Neuro-Symbolic Execution: The Feasibility of an Inductive Approach to Symbolic Execution
• Variable Selection with Rigorous Uncertainty Quantification using Deep Bayesian Neural Networks: Posterior Concentration and Bernstein-von Mises Phenomenon
• A Probabilistic Disease Progression Model for Predicting Future Clinical Outcome
• Cross-Domain Generalization of Neural Constituency Parsers
• Methods of machine learning for the analysis of cosmic rays mass composition with the KASCADE experiment data
• A Memory Augmented Architecture for Continuous Speaker Identification in Meetings
• MDReg-Net: Multi-resolution diffeomorphic image registration using fully convolutional networks with deep self-supervision
• Tensor Relational Algebra for Machine Learning System Design
• Topological Gradient-based Competitive Learning
• Data-informed Deep Optimization
• Federated Learning is Better with Non-Homomorphic Encryption
• Towards Query Efficient Black-box Attacks: An Input-free Perspective
• Agatha: Smart Contract for DNN Computation
• Water Isotope Separation using Deep Learning and a Catalytically Active Ultrathin Membrane
• MeDaS: An open-source platform as service to help break the walls between medicine and informatics
• Predicting Missing Information of Key Aspects in Vulnerability Reports
• Distributed Optimization for Client-Server Architecture with Negative Gradient Weights
• A Sensitivity Analysis of Attention-Gated Convolutional Neural Networks for Sentence Classification
• FENXI: Deep-learning Traffic Analytics at the Edge
• Decomposing reverse-mode automatic differentiation
• PyTorch Tabular: A Framework for Deep Learning with Tabular Data
• TensorFlow with user friendly Graphical Framework for object detection API
• Adversarial methods to reduce simulation bias in neutrino interaction event filtering at Liquid Argon Time Projection Chambers
• Deep Data Flow Analysis
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• Unsupervised Explanation Generation for Machine Reading Comprehension
• Software implemented fault diagnosis of natural gas pumping unit based on feedforward neural network
• OSTSC: Over Sampling for Time Series Classification in R
• Efficient Optimization Methods for Extreme Similarity Learning with Nonlinear Embeddings
• Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs
• End-to-end Sampling Patterns
• Accelerating Multi-Model Inference by Merging DNNs of Different Weights
• Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes
• Derivatives of partial eigendecomposition of a real symmetric matrix for degenerate cases
• EasyFL: A Low-code Federated Learning Platform For Dummies
• Python Implementation of the Dynamic Distributed Dimensional Data Model
• Self-Claimed Assumptions in Deep Learning Frameworks: An Exploratory Study
• Embedding Cardinality Constraints in Neural Link Predictors
• Few-Shot Object Recognition from Machine-Labeled Web Images
• Detecting Speaker Personas from Conversational Texts
• Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation
• Exploring Contextualized Neural Language Models for Temporal Dependency Parsing
• Matrix-Free Preconditioning in Online Learning
• RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials
• Paranom: A Parallel Anomaly Dataset Generator
• Separate and Attend in Personal Email Search
• Good Intentions: Adaptive Parameter Management via Intent Signaling
• TyXe: Pyro-based Bayesian neural nets for Pytorch
• DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings
• A neural network to classify metaphorical violence on cable news
• DELMU: A Deep Learning Approach to Maximising the Utility of Virtualised Millimetre-Wave Backhauls
• Transferability of Operational Status Classification Models Among Different Wind Turbine Typesq
• Online Evolutionary Batch Size Orchestration for Scheduling Deep Learning Workloads in GPU Clusters
• Improving Counterfactual Generation for Fair Hate Speech Detection
• Sampling from Stochastic Finite Automata with Applications to CTC Decoding
• Dataset Bias Mitigation Through Analysis of CNN Training Scores
• Improving Compositional Generalization in Classification Tasks via Structure Annotations
• LyricJam: A system for generating lyrics for live instrumental music
• A constrained recursion algorithm for batch normalization of tree-sturctured LSTM
• Transparent Synchronous Dataflow
• Programming with Neural Surrogates of Programs
• A Structured Learning Approach with Neural Conditional Random Fields for Sleep Staging
• TextAttack: Lessons learned in designing Python frameworks for NLP
• Generative Creativity: Adversarial Learning for Bionic Design
• When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence
• InSPECtor: an end-to-end design framework for compressive pixelated hyperspectral instruments
• Improving the quality of Persian clinical text with a novel spelling correction system
• Machine Learning Systems for Intelligent Services in the IoT: A Survey
• Bio-inspired visual relative localization for large swarms of UAVs
• A Retrospective of the Tutorial on Opportunities and Challenges of Online Deep Learning
• Deep Physiological State Space Model for Clinical Forecasting
• ByzShield: An Efficient and Robust System for Distributed Training
• Accelerating E-Commerce Search Engine Ranking by Contextual Factor Selection
• Explainable Biomedical Recommendations via Reinforcement Learning Reasoning on Knowledge Graphs
• Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation
• Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation
• A Neural Emulator for Uncertainty Estimation of Fire Propagation
• NLP Workbench: Efficient and Extensible Integration of State-of-the-art Text Mining Tools
• Deep Learning with Apache SystemML
• Generalized Doubly Reparameterized Gradient Estimators
• ECRM: Efficient Fault Tolerance for Recommendation Model Training via Erasure Coding
• Fast Approximation of Optimal Perturbed Long-Duration Impulsive Transfers via Deep Neural Networks
• Deep Learning Features for Robust Detection of Acoustic Events in Sleep-Disordered Breathing
• Identifying the Quantum Properties of Hadronic Resonances using Machine Learning
• Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks
• Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing
• Active Sampling Count Sketch (ASCS) for Online Sparse Estimation of a Trillion Scale Covariance Matrix
• Learning Consumer and Producer Embeddings for User-Generated Content Recommendation
• HetSeq: Distributed GPU Training on Heterogeneous Infrastructure
• Photometric Search for Exomoons by using Convolutional Neural Networks
• CloudifierNet -- Deep Vision Models for Artificial Image Processing
• Conflict and Cooperation: AI Research and Development in terms of the Economy of Conventions
• Sonic: A Sampling-based Online Controller for Streaming Applications
• DIFFnet: Diffusion parameter mapping network generalized for input diffusion gradient schemes and bvalues
• Towards Expectation-Maximization by SQL in RDBMS
• A real-time hourly ozone prediction system using deep convolutional neural network
• Data Dwarfs: A Lens Towards Fully Understanding Big Data and AI Workloads
• Impact of neutral fluxes and signal significance optimization on semi-exclusive $pp\to t\bar{t}$ production via deep learning training
• Analysis of Macula on Color Fundus Images Using Heightmap Reconstruction Through Deep Learning
• Modelling brain lesion volume in patches with CNN-based Poisson Regression
• Towards A Methodology and Framework for Workflow-Driven Team Science
• Lily-like twist distribution in toroidal nematics
• Are My Invariants Valid? A Learning Approach
• Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots
• On the complexity of nonsmooth automatic differentiation
• Counter-Interference Adapter for Multilingual Machine Translation
• Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
• Learning disentangled representation for classical models
• Predicting In-game Actions from Interviews of NBA Players
• A Generic Solver for Unconstrained Control Problems with Integral Functional Objectives
• Neko: a Library for Exploring Neuromorphic Learning Rules
• Bidirectional Multirate Reconstruction for Temporal Modeling in Videos
• Physics-Informed Deep Learning Characterizes Morphodynamics of Asian Soybean Rust Disease
• Towards Comparative Physical Interpretation of Spatial Variability Aware Neural Networks: A Summary of Results
• Dynamic Gradient Aggregation for Federated Domain Adaptation
• Separation of Water and Fat Magnetic Resonance Imaging Signals Using Deep Learning with Convolutional Neural Networks
• Photometric redshifts for the S-PLUS Survey: is machine learning up to the task?
• Accelerating drug repurposing for COVID-19 via modeling drug mechanism of action with large scale gene-expression profiles
• REVE: Regularizing Deep Learning with Variational Entropy Bound
• BiCANet: Bi-directional Contextual Aggregating Network for Image Semantic Segmentation
• Ricci-Notation Tensor Framework for Model-based Approaches to Imaging
• Features of a Splashing Drop on a Solid Surface and the Temporal Evolution extracted through Image-Sequence Classification using an Interpretable Feedforward Neural Network
• From Binary Error Correcting Codes to a Relation Between Maximal D=4 and D=3 Supergravities
• Machine learning in physics: The pitfalls of poisoned training sets
• Towards Interpretable and Learnable Risk Analysis for Entity Resolution
• Building your Cross-Platform Application with RHEEM
• Semantic Preserving Generative Adversarial Models
• Distributed Caching for Complex Querying of Raw Arrays
• GLISSE: A GPU-optimized planetary system integrator with application to orbital stability calculations
• Towards Deep and Representation Learning for Talent Search at LinkedIn
• Feature Tracking Cardiac Magnetic Resonance via Deep Learning and Spline Optimization
• Parallel Binary Code Analysis