Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Abstract

In this paper we compare different types of recurrent units in recurrent neural networks (RNNs). Especially, we focus on more sophisticated units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU). We evaluate these recurrent units on the tasks of polyphonic music modeling and speech signal modeling. Our experiments revealed that these advanced recurrent units are indeed better than more traditional recurrent units such as tanh units. Also, we found GRU to be comparable to LSTM.

arXiv commentPresented in NIPS 2014 Deep Learning and Representation Learning Workshop

References in corpus (4)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Theano: new features and speed improvements
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
• Pylearn2: a machine learning research library

Cited by in corpus (1555)

• LSTM: A Search Space Odyssey
• A Survey on Visual Transformer
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
• Pre-trained Models for Natural Language Processing: A Survey
• Deep Learning in Spiking Neural Networks
• Recent Trends in Deep Learning Based Natural Language Processing
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Recurrent Neural Network for Text Classification with Multi-Task Learning
• PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
• Comparative Study of CNN and RNN for Natural Language Processing
• Visualizing and Understanding Recurrent Networks
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Skip-Thought Vectors
• A Survey and Critique of Multiagent Deep Reinforcement Learning
• Deep Learning in Medical Image Registration: A Review
• End-To-End Memory Networks
• A Survey on Evolutionary Neural Architecture Search
• Social physics
• SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
• Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
• Human Action Recognition from Various Data Modalities: A Review
• KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics
• Recent Advances in Recurrent Neural Networks
• Deep Learning for Time Series Anomaly Detection: A Survey
• Quantum advantage in learning from experiments
• Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
• Deep Reinforcement Learning: An Overview
• SpeechBrain: A General-Purpose Speech Toolkit
• Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
• Multimodal Intelligence: Representation Learning, Information Fusion, and Applications
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
• Image and Video Compression with Neural Networks: A Review
• Understanding Neural Networks through Representation Erasure
• Recurrent Neural Networks For Accurate RSSI Indoor Localization
• Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning
• Light Gated Recurrent Units for Speech Recognition
• QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension
• Artificial neural networks for neuroscientists: A primer
• Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction
• Deep Voice: Real-time Neural Text-to-Speech
• Unsupervised and Semi-supervised Anomaly Detection with LSTM Neural Networks
• Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyond
• Conditional Time Series Forecasting with Convolutional Neural Networks
• Wave Physics as an Analog Recurrent Neural Network
• Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
• Self-attention for raw optical Satellite Time Series Classification
• DyNet: The Dynamic Neural Network Toolkit
• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• Hello Edge: Keyword Spotting on Microcontrollers
• A Comprehensive Survey on Deep Graph Representation Learning
• Recent Trends in Deep Learning Based Personality Detection
• Reconstructing quantum states with generative models
• Early Stage Malware Prediction Using Recurrent Neural Networks
• Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books
• MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection
• Ask the GRU: Multi-Task Learning for Deep Text Recommendations
• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• Working Memory Connections for LSTM
• An overview and comparative analysis of Recurrent Neural Networks for Short Term Load Forecasting
• DeepNano: Deep Recurrent Neural Networks for Base Calling in MinION Nanopore Reads
• Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
• Evaluation of deep learning models for multi-step ahead time series prediction
• Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities
• Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
• Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos
• Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis
• Residual Gated Graph ConvNets
• TI-CNN: Convolutional Neural Networks for Fake News Detection
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN
• Online and Linear-Time Attention by Enforcing Monotonic Alignments
• A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances
• Neural GPUs Learn Algorithms
• A Gated Recurrent Unit Approach to Bitcoin Price Prediction
• Improving Chemical Autoencoder Latent Space and Molecular De novo Generation Diversity with Heteroencoders
• QuaterNet: A Quaternion-based Recurrent Model for Human Motion
• LipNet: End-to-End Sentence-level Lipreading
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• On Extended Long Short-term Memory and Dependent Bidirectional Recurrent Neural Network
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• Patient2Vec: A Personalized Interpretable Deep Representation of the Longitudinal Electronic Health Record
• A Deep-Learning Intelligent System Incorporating Data Augmentation for Short-Term Voltage Stability Assessment of Power Systems
• Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information
• Neural Machine Translation Inspired Binary Code Similarity Comparison beyond Function Pairs
• A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
• Network-wide traffic signal control optimization using a multi-agent deep reinforcement learning
• GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
• The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Visual Entailment: A Novel Task for Fine-Grained Image Understanding
• Social Interactions for Autonomous Driving: A Review and Perspectives
• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• Modeling Coverage for Neural Machine Translation
• DeepMood: Modeling Mobile Phone Typing Dynamics for Mood Detection
• How Much Can CLIP Benefit Vision-and-Language Tasks?
• Bayesian-Deep-Learning Estimation of Earthquake Location from Single-Station Observations
• VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
• Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• Modeling Human Motion with Quaternion-based Neural Networks
• HiPPO: Recurrent Memory with Optimal Polynomial Projections
• Deep Learning and Its Applications to Machine Health Monitoring: A Survey
• Tacotron: Towards End-to-End Speech Synthesis
• Delving Deeper into Convolutional Networks for Learning Video Representations
• Neural Entity Linking: A Survey of Models Based on Deep Learning
• Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code
• Click-Through Rate Prediction in Online Advertising: A Literature Review
• Improvement in Land Cover and Crop Classification based on Temporal Features Learning from Sentinel-2 Data Using Recurrent-Convolutional Neural Network (R-CNN)
• Efficient softmax approximation for GPUs
• Heterogeneous Task Offloading and Resource Allocations via Deep Recurrent Reinforcement Learning in Partial Observable Multi-Fog Networks
• Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
• Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
• EsDNN: Deep Neural Network based Multivariate Workload Prediction Approach in Cloud Environment
• Stabilizing Transformers for Reinforcement Learning
• Recurrent Neural Networks: An Embedded Computing Perspective
• Taming the latency in multi-user VR 360${}^{\circ }$: A QoE-aware deep learning-aided multicast framework
• Applications of deep learning in traffic congestion detection, prediction and alleviation: A survey
• Gaze-in-wild: A dataset for studying eye and head coordination in everyday activities
• Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks
• Continual Learning for Recurrent Neural Networks: an Empirical Evaluation
• DeepBach: a Steerable Model for Bach Chorales Generation
• Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples
• Multilogue-Net: A Context Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• EEGFuseNet: Hybrid Unsupervised Deep Feature Characterization and Fusion for High-Dimensional EEG with An Application to Emotion Recognition
• Disentangling Long and Short-Term Interests for Recommendation
• Deep Learning and Knowledge-Based Methods for Computer Aided Molecular Design -- Toward a Unified Approach: State-of-the-Art and Future Directions
• Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
• DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
• CODIT: Code Editing with Tree-Based Neural Models
• Generating and designing DNA with deep generative models
• On the Convergence Rate of Training Recurrent Neural Networks
• Compressing Recurrent Neural Network with Tensor Train
• Contextual Hybrid Session-based News Recommendation with Recurrent Neural Networks
• MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
• STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction
• Review: Deep Learning in Electron Microscopy
• Learning to Generate Questions by Learning What not to Generate
• GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendation
• ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation
• DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
• Gait Recognition Based on Deep Learning: A Survey
• Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
• Neural Map: Structured Memory for Deep Reinforcement Learning
• A Survey of Deep Learning Techniques for Neural Machine Translation
• A Hybrid RNN-HMM Approach for Weakly Supervised Temporal Action Segmentation
• Domain Adaptive Fake News Detection via Reinforcement Learning
• Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
• Interpreting Deep Learning-Based Networking Systems
• Generative Models for Automatic Chemical Design
• Flexible statistical inference for mechanistic models of neural dynamics
• Benchmarking of eight recurrent neural network variants for breath phase and adventitious sound detection on a self-developed open-access lung sound database-HF_Lung_V1
• Linguistically Regularized LSTMs for Sentiment Classification
• Deep Gated Recurrent and Convolutional Network Hybrid Model for Univariate Time Series Classification
• Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
• End-to-End ASR-free Keyword Search from Speech
• Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
• Adversarial Multi-task Learning for Text Classification
• R-Transformer: Recurrent Neural Network Enhanced Transformer
• From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities
• Interpretable Convolutional Filters with SincNet
• Where to put the Image in an Image Caption Generator
• Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities
• THUMT: An Open Source Toolkit for Neural Machine Translation
• Finding beans in burgers: Deep semantic-visual embedding with localization
• Learning Longer-term Dependencies in RNNs with Auxiliary Losses
• Neural Models for Information Retrieval
• Autoregressive Convolutional Neural Networks for Asynchronous Time Series
• Low-Resource Knowledge-Grounded Dialogue Generation
• Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
• Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers
• OpenNMT: Neural Machine Translation Toolkit
• Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials
• A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
• Overcoming the vanishing gradient problem in plain recurrent networks
• Memory-augmented Dense Predictive Coding for Video Representation Learning
• A Novel Deep Neural Network Architecture for Real-Time Water Demand Forecasting
• DepressionNet: A Novel Summarization Boosted Deep Framework for Depression Detection on Social Media
• Pay Attention to Evolution: Time Series Forecasting with Deep Graph-Evolution Learning
• Machine Learning vs Statistical Methods for Time Series Forecasting: Size Matters
• Dive into Deep Learning
• Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
• Recurrent Neural Networks for Time Series Forecasting
• Analyzing Human-Human Interactions: A Survey
• Survey on Machine Learning for Traffic-Driven Service Provisioning in Optical Networks
• Application of generative autoencoder in de novo molecular design
• DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
• Does Multimodality Help Human and Machine for Translation and Image Captioning?
• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention
• Long-term Forecasting using Higher Order Tensor RNNs
• LFADS - Latent Factor Analysis via Dynamical Systems
• Efficient Neural Audio Synthesis
• Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models
• Attention-Based Deep Learning Framework for Human Activity Recognition with User Adaptation
• Interaction networks for the identification of boosted $H\to b\overline{b}$ decays
• SleePyCo: Automatic Sleep Scoring with Feature Pyramid and Contrastive Learning
• Character-based Joint Segmentation and POS Tagging for Chinese using Bidirectional RNN-CRF
• DeepTrack: Lightweight Deep Learning for Vehicle Path Prediction in Highways
• Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
• Feedforward Sequential Memory Networks: A New Structure to Learn Long-term Dependency
• Neural Abstractive Text Summarization with Sequence-to-Sequence Models
• Table Structure Extraction with Bi-directional Gated Recurrent Unit Networks
• Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
• Learning temporal data with variational quantum recurrent neural network
• Aspect Based Sentiment Analysis with Gated Convolutional Networks
• Unsupervised Deep Learning for IoT Time Series
• Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load
• Failures of Gradient-Based Deep Learning
• Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows
• Hurricane Forecasting: A Novel Multimodal Machine Learning Framework
• Instance-Specific Feature Propagation for Referring Segmentation
• Effective Quantization Methods for Recurrent Neural Networks
• A Radar Signal Deinterleaving Method Based on Semantic Segmentation with Neural Network
• Improved Recurrent Neural Networks for Session-based Recommendations
• Document Context Language Models
• Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty
• Semantic Tagging with Deep Residual Networks
• Deep Reinforcement Learning-based Image Captioning with Embedding Reward
• Domain Adversarial Spatial-Temporal Network: A Transferable Framework for Short-term Traffic Forecasting across Cities
• Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction
• Recurrent Slice Networks for 3D Segmentation of Point Clouds
• Machine learning for music genre: multifaceted review and experimentation with audioset
• LoBSTr: Real-time Lower-body Pose Prediction from Sparse Upper-body Tracking Signals
• Towards Neural Network-based Reasoning
• Automatic Detection of Malware-Generated Domains with Recurrent Neural Models
• Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation
• Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets
• Learning Long-Term Dependencies in Irregularly-Sampled Time Series
• Neural Networks for Text Correction and Completion in Keyboard Decoding
• A Memory-Network Based Solution for Multivariate Time-Series Forecasting
• Predicting Temporal Sets with Deep Neural Networks
• Delta Descriptors: Change-Based Place Representation for Robust Visual Localization
• Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
• Zero-Shot Action Recognition in Videos: A Survey
• Neural Machine Translation with External Phrase Memory
• EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction
• FAKEDETECTOR: Effective Fake News Detection with Deep Diffusive Neural Network
• Language learning using Speech to Image retrieval
• Deep Learning for Sentiment Analysis : A Survey
• Graph-MLP: Node Classification without Message Passing in Graph
• Zero-Resource Knowledge-Grounded Dialogue Generation
• Graph-based Neural Multi-Document Summarization
• Interpreting recurrent neural networks behaviour via excitable network attractors
• Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods
• From Fourier to Koopman: Spectral Methods for Long-term Time Series Prediction
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
• Learning text representation using recurrent convolutional neural network with highway layers
• Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions
• Aspect-Based Sentiment Analysis Using a Two-Step Neural Network Architecture
• Video Storytelling: Textual Summaries for Events
• Advances in Quantum Deep Learning: An Overview
• Beyond Narrative Description: Generating Poetry from Images by Multi-Adversarial Training
• Molecular Generation with Recurrent Neural Networks (RNNs)
• Automated Audio Captioning: An Overview of Recent Progress and New Challenges
• Unsupervised Text Style Transfer using Language Models as Discriminators
• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• Maybe Deep Neural Networks are the Best Choice for Modeling Source Code
• Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies
• Geometric deep learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity
• Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation
• Neural Information Retrieval: A Literature Review
• A Survey of Optimization Methods from a Machine Learning Perspective
• Motif-based Graph Self-Supervised Learning for Molecular Property Prediction
• Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
• Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting
• Deep Coordination Graphs
• Supervised and Semi-supervised Deep Probabilistic Models for Indoor Positioning Problems
• A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data
• Robust and Subject-Independent Driving Manoeuvre Anticipation through Domain-Adversarial Recurrent Neural Networks
• Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts
• Delta Networks for Optimized Recurrent Network Computation
• Uncovering Temporal Context for Video Question and Answering
• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
• LightRNN: Memory and Computation-Efficient Recurrent Neural Networks
• Reinforced Mnemonic Reader for Machine Reading Comprehension
• Sequential Decision Fusion for Environmental Classification in Assistive Walking
• Neural Predictive Belief Representations
• Deep Learning with Functional Inputs
• Message-Passing Neural Networks Learn Little's Law
• Speaker Adaptation for Attention-Based End-to-End Speech Recognition
• Visually grounded models of spoken language: A survey of datasets, architectures and evaluation techniques
• Neural ranking models for document retrieval
• Proactive Human-Machine Conversation with Explicit Conversation Goals
• PlaTe: Visually-Grounded Planning with Transformers in Procedural Tasks
• Toward automatic generation of control structures for process flow diagrams with large language models
• An Introductory Survey on Attention Mechanisms in NLP Problems
• Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction
• Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction
• No-Reference Image Quality Assessment by Hallucinating Pristine Features
• Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning
• DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning
• Ray Interference: a Source of Plateaus in Deep Reinforcement Learning
• Deep Implicit Coordination Graphs for Multi-agent Reinforcement Learning
• Recurrent Spatial Transformer Networks
• An empirical study on the effectiveness of images in Multimodal Neural Machine Translation
• Exploiting Positional Information for Session-based Recommendation
• Compositional Memory for Visual Question Answering
• Sequence Modeling via Segmentations
• Nonlinear MPC for Offset-Free Tracking of systems learned by GRU Neural Networks
• Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
• Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings
• AdaRNN: Adaptive Learning and Forecasting of Time Series
• An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)
• MSED: a multi-modal sleep event detection model for clinical sleep analysis
• MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction
• Classifying Process Instances Using Recurrent Neural Networks
• Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark
• Ballistocardiogram artifact reduction in simultaneous EEG-fMRI using deep learning
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Abstractive and Extractive Text Summarization using Document Context Vector and Recurrent Neural Networks
• Towards High Performance Video Object Detection for Mobiles
• 3G structure for image caption generation
• Learning to Select, Track, and Generate for Data-to-Text
• Recurrent neural networks and transfer learning for elasto-plasticity in woven composites
• Latent Attention For If-Then Program Synthesis
• Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform
• Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
• Network On Network for Tabular Data Classification in Real-world Applications
• Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
• Dropout Feature Ranking for Deep Learning Models
• State-of-the-art Speech Recognition using EEG and Towards Decoding of Speech Spectrum From EEG
• Exploring Self-Supervised Representation Ensembles for COVID-19 Cough Classification
• Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
• Exploring the Generalizability of Spatio-Temporal Traffic Prediction: Meta-Modeling and an Analytic Framework
• Neural Enhanced Belief Propagation on Factor Graphs
• Neural Generative Question Answering
• Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
• A Taxonomy for Neural Memory Networks
• Deep Conversational Recommender in Travel
• Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation
• SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction
• Autoregressive Coefficients based Intelligent Protection of Transmission Lines Connected to Type-3 Wind Farms
• The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions
• Conversational Emotion Analysis via Attention Mechanisms
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• Aspect Category Detection via Topic-Attention Network
• Legal Document Classification: An Application to Law Area Prediction of Petitions to Public Prosecution Service
• Deep Music Analogy Via Latent Representation Disentanglement
• Explicit Time Embedding Based Cascade Attention Network for Information Popularity Prediction
• Unconditional Audio Generation with Generative Adversarial Networks and Cycle Regularization
• Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models
• Neural-network learning of SPOD latent dynamics
• Predicting Drivers' Route Trajectories in Last-Mile Delivery Using A Pair-wise Attention-based Pointer Neural Network
• An End-to-End Architecture for Keyword Spotting and Voice Activity Detection
• Multi-modal gated recurrent units for image description
• UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers
• Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System
• Cortical microcircuits as gated-recurrent neural networks
• Cryptocurrency Trading: A Comprehensive Survey
• Neural Word Segmentation Learning for Chinese
• CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
• Gated Recurrent Neural Tensor Network
• Multivariate Time-series Anomaly Detection via Graph Attention Network
• SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification
• Improving the Gating Mechanism of Recurrent Neural Networks
• Discrete Event, Continuous Time RNNs
• R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting
• Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
• Learning to Extract Coherent Summary via Deep Reinforcement Learning
• SVFAP: Self-supervised Video Facial Affect Perceiver
• MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks
• Semi-Supervised QA with Generative Domain-Adaptive Nets
• Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
• Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
• GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
• Structured Attention for Unsupervised Dialogue Structure Induction
• A multi-task learning model for malware classification with useful file access pattern from API call sequence
• AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks
• Towards Making the Most of BERT in Neural Machine Translation
• Recurrent Neural Network-based Internal Model Control design for stable nonlinear systems
• Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencoder
• Text-based Localization of Moments in a Video Corpus
• Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search
• RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music
• Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
• Speaker Diarization with Lexical Information
• Keyword Decisions in Sponsored Search Advertising: A Literature Review and Research Agenda
• Iterative Visual Reasoning Beyond Convolutions
• Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural Networks
• Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
• Time-Aware Gated Recurrent Unit Networks for Road Surface Friction Prediction Using Historical Data
• Neural Machine Translation with Supervised Attention
• E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction
• Modeling Multi-aspect Preferences and Intents for Multi-behavioral Sequential Recommendation
• A GRU-Gated Attention Model for Neural Machine Translation
• Composite Motion Learning with Task Control
• AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization
• Leveraging Multilingual Transformers for Hate Speech Detection
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• IcoRating: A Deep-Learning System for Scam ICO Identification
• Uncertainty-Aware Reliable Text Classification
• Modeling and Control of a Reconfigurable Photonic Circuit using Deep Learning
• Understanding Hidden Memories of Recurrent Neural Networks
• Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
• A Deep Memory-based Architecture for Sequence-to-Sequence Learning
• A bio-inspired bistable recurrent cell allows for long-lasting memory
• Transcribing Content from Structural Images with Spotlight Mechanism
• Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
• Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
• A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture content
• Unsupervised temporal context learning using convolutional neural networks for laparoscopic workflow analysis
• Image-Conditioned Graph Generation for Road Network Extraction
• The Echo Index and multistability in input-driven recurrent neural networks
• VoiceFixer: Toward General Speech Restoration with Neural Vocoder
• Deep Sequence Modeling: Development and Applications in Asset Pricing
• Causal Navigation by Continuous-time Neural Networks
• Query-Based Abstractive Summarization Using Neural Networks
• Explanation as a Defense of Recommendation
• EENMF: An End-to-End Neural Matching Framework for E-Commerce Sponsored Search
• BanditSum: Extractive Summarization as a Contextual Bandit
• Accurately and Efficiently Interpreting Human-Robot Instructions of Varying Granularities
• Named Entity Recognition with stack residual LSTM and trainable bias decoding
• KOHTD: Kazakh Offline Handwritten Text Dataset
• Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks
• Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems
• NUVA: A Naming Utterance Verifier for Aphasia Treatment
• HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information
• The Portiloop: a deep learning-based open science tool for closed-loop brain stimulation
• Multi-Time Attention Networks for Irregularly Sampled Time Series
• Iterative Retraining of Quantum Spin Models Using Recurrent Neural Networks
• Neural Language Generation: Formulation, Methods, and Evaluation
• Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
• Accelerating Neural Transformer via an Average Attention Network
• Improving Long-Horizon Forecasts with Expectation-Biased LSTM Networks
• From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning
• Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning
• Learning with hidden variables
• LCSTS: A Large Scale Chinese Short Text Summarization Dataset
• Continuous Gesture Recognition from sEMG Sensor Data with Recurrent Neural Networks and Adversarial Domain Adaptation
• A Hybrid Retrieval-Generation Neural Conversation Model
• Meta-Learning Deep Energy-Based Memory Models
• Hierarchical Attention-Based Recurrent Highway Networks for Time Series Prediction
• Visual Semantic Reasoning for Image-Text Matching
• Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition
• MultiBench: Multiscale Benchmarks for Multimodal Representation Learning
• Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation
• The model of an anomaly detector for HiLumi LHC magnets based on Recurrent Neural Networks and adaptive quantization
• Chat Detection in an Intelligent Assistant: Combining Task-oriented and Non-task-oriented Spoken Dialogue Systems
• Deriving Neural Architectures from Sequence and Graph Kernels
• Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals
• False News On Social Media: A Data-Driven Survey
• Visual Grounding of Learned Physical Models
• Transformer Hawkes Process
• Recurrent Memory Networks for Language Modeling
• A Deep Recurrent Q Network towards Self-adapting Distributed Microservices architecture
• End2You -- The Imperial Toolkit for Multimodal Profiling by End-to-End Learning
• Embodied Visual Recognition
• Large-Scale User Modeling with Recurrent Neural Networks for Music Discovery on Multiple Time Scales
• Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation
• Algorithmic Composition of Melodies with Deep Recurrent Neural Networks
• LabelSens: Enabling Real-time Sensor Data Labelling at the point of Collection on Edge Computing
• An Adaptive, Context-Aware, and Stacked Attention Network-Based Recommendation System to Capture Users' Temporal Preference
• A Survey of COVID-19 Misinformation: Datasets, Detection Techniques and Open Issues
• Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing
• Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task
• A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series
• Highrisk Prediction from Electronic Medical Records via Deep Attention Networks
• Feedforward Sequential Memory Neural Networks without Recurrent Feedback
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
• A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes
• Robust constrained nonlinear Model Predictive Control with Gated Recurrent Unit model -- Extended version
• Uncertainty on Asynchronous Time Event Prediction
• Review of end-to-end speech synthesis technology based on deep learning
• Scale-recurrent Network for Deep Image Deblurring
• Label Dependent Attention Model for Disease Risk Prediction Using Multimodal Electronic Health Records
• STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
• Basis Pursuit Denoising via Recurrent Neural Network Applied to Super-resolving SAR Tomography
• Residual or Gate? Towards Deeper Graph Neural Networks for Inductive Graph Representation Learning
• Exploration of Neural Machine Translation in Autoformalization of Mathematics in Mizar
• Sequential Context Encoding for Duplicate Removal
• Towards Conversational Recommendation over Multi-Type Dialogs
• Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Tagging
• Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models
• Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study
• Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition
• Learning compositionally through attentive guidance
• Comparison of Deep learning models on time series forecasting : a case study of Dissolved Oxygen Prediction
• Learning to Count Isomorphisms with Graph Neural Networks
• Cross-hospital Sepsis Early Detection via Semi-supervised Optimal Transport with Self-paced Ensemble
• Identifying tax evasion in Mexico with tools from network science and machine learning
• Transferring Cross-domain Knowledge for Video Sign Language Recognition
• Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data
• MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks
• Scaling up DNA digital data storage by efficiently predicting DNA hybridisation using deep learning
• Seq2Emo for Multi-label Emotion Classification Based on Latent Variable Chains Transformation
• Stories for Images-in-Sequence by using Visual and Narrative Components
• Collaborative Visual Navigation
• Multichannel CNN with Attention for Text Classification
• A Novel Ensemble Deep Learning Model for Stock Prediction Based on Stock Prices and News
• A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting
• Representation-Aggregation Networks for Segmentation of Multi-Gigapixel Histology Images
• Fully Transformer-Equipped Architecture for End-to-End Referring Video Object Segmentation
• Sequential Attention Source Identification Based on Feature Representation
• Quo Vadis: Hybrid Machine Learning Meta-Model based on Contextual and Behavioral Malware Representations
• A generative model for molecule generation based on chemical reaction trees
• On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
• Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering
• Comparative Explanations of Recommendations
• Federated Learning of N-gram Language Models
• CS-TGN: Community Search via Temporal Graph Neural Networks
• A machine learning and feature engineering approach for the prediction of the uncontrolled re-entry of space objects
• Investigating gated recurrent neural networks for speech synthesis
• Recent Advances and Trends in Multimodal Deep Learning: A Review
• CycleSense: Detecting Near Miss Incidents in Bicycle Traffic from Mobile Motion Sensors
• Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval
• Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
• Scenario-Transferable Semantic Graph Reasoning for Interaction-Aware Probabilistic Prediction
• Improving Background Based Conversation with Context-aware Knowledge Pre-selection
• Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction
• Voice Conversion with Conditional SampleRNN
• Temporal Recurrent Networks for Online Action Detection
• Can recurrent neural networks warp time?
• HyperST-Net: Hypernetworks for Spatio-Temporal Forecasting
• Positivity Bias in Customer Satisfaction Ratings
• Recurrent Attention Unit
• Improving Interpretability of Deep Neural Networks with Semantic Information
• Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering
• State space models for building control: how deep should you go?
• Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning
• Deep reinforcement learning for time series: playing idealized trading games
• Predicting User Emotional Tone in Mental Disorder Online Communities
• AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting
• Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference
• SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders
• Adversarial TableQA: Attention Supervision for Question Answering on Tables
• RDIS: Random Drop Imputation with Self-Training for Incomplete Time Series Data
• Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
• Unfolding AIS transmission behavior for vessel movement modeling on noisy data leveraging machine learning
• From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
• Multi-period Time Series Modeling with Sparsity via Bayesian Variational Inference
• Modelling Sentence Pairs with Tree-structured Attentive Encoder
• Are Emojis Predictable?
• Deep Audio-Visual Learning: A Survey
• Gate Activation Signal Analysis for Gated Recurrent Neural Networks and Its Correlation with Phoneme Boundaries
• Representation of linguistic form and function in recurrent neural networks
• TTS-Portuguese Corpus: a corpus for speech synthesis in Brazilian Portuguese
• Empirical Analysis of Multi-Task Learning for Reducing Model Bias in Toxic Comment Detection
• Learning to Globally Edit Images with Textual Description
• The Statistical Recurrent Unit
• RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
• Compositionality decomposed: how do neural networks generalise?
• Deep Retrieval-Based Dialogue Systems: A Short Review
• Virtual-to-Real-World Transfer Learning for Robots on Wilderness Trails
• MojiTalk: Generating Emotional Responses at Scale
• PTP: Parallelized Tracking and Prediction with Graph Neural Networks and Diversity Sampling
• Deep Learning for Lip Reading using Audio-Visual Information for Urdu Language
• SeqNAS: Neural Architecture Search for Event Sequence Classification
• Style Imitation and Chord Invention in Polyphonic Music with Exponential Families
• Neural Personalized Response Generation as Domain Adaptation
• Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
• Insights into End-to-End Learning Scheme for Language Identification
• Context Gates for Neural Machine Translation
• Multi-year Long-term Load Forecast for Area Distribution Feeders based on Selective Sequence Learning
• Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
• Separating Answers from Queries for Neural Reading Comprehension
• Context-aware Biaffine Localizing Network for Temporal Sentence Grounding
• A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation
• Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning
• CD-ROM: Complemented Deep-Reduced Order Model
• Robustness Analysis of Visual QA Models by Basic Questions
• VQABQ: Visual Question Answering by Basic Questions
• FlipDial: A Generative Model for Two-Way Visual Dialogue
• A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
• Deep Reinforcement Learning for Event-Triggered Control
• HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition
• Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data
• Aspect-Based Relational Sentiment Analysis Using a Stacked Neural Network Architecture
• End-to-end Learning for 3D Facial Animation from Raw Waveforms of Speech
• Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning
• LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
• Eve: A Gradient Based Optimization Method with Locally and Globally Adaptive Learning Rates
• Deep Residual Network for Sound Source Localization in the Time Domain
• Automatic Judgment Prediction via Legal Reading Comprehension
• Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation
• Cross-lingual Candidate Search for Biomedical Concept Normalization
• Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
• Using a thousand optimization tasks to learn hyperparameter search strategies
• Incremental Dense Reconstruction from Monocular Video with Guided Sparse Feature Volume Fusion
• PixelVAE++: Improved PixelVAE with Discrete Prior
• ATOM: Commit Message Generation Based on Abstract Syntax Tree and Hybrid Ranking
• Robust Trajectory Forecasting for Multiple Intelligent Agents in Dynamic Scene
• The Winning Solution to the IEEE CIG 2017 Game Data Mining Competition
• DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation
• The Architectural Implications of Facebook's DNN-based Personalized Recommendation
• Learning semantic sentence representations from visually grounded language without lexical knowledge
• Automatic classification of eclipsing binary stars using deep learning methods
• Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
• EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation
• Exploring the Landscape of Ubiquitous In-home Health Monitoring: A Comprehensive Survey
• Temperature check: theory and practice for training models with softmax-cross-entropy losses
• Variational Autoencoder for Anti-Cancer Drug Response Prediction
• Explicit Interaction Model towards Text Classification
• Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
• DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
• Zoom Better to See Clearer: Human and Object Parsing with Hierarchical Auto-Zoom Net
• SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization
• Efficient Convolutional Neural Network Training with Direct Feedback Alignment
• Large-scale weakly supervised audio classification using gated convolutional neural network
• PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions
• A Dual-Stream Recurrence-Attention Network With Global-Local Awareness for Emotion Recognition in Textual Dialog
• Machine Learning for Detecting Data Exfiltration: A Review
• CKConv: Continuous Kernel Convolution For Sequential Data
• Toward Multimodal Model-Agnostic Meta-Learning
• Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values
• Semantic Video Segmentation by Gated Recurrent Flow Propagation
• A CNN-LSTM Quantifier for Single Access Point CSI Indoor Localization
• Style Example-Guided Text Generation using Generative Adversarial Transformers
• Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters
• Fine-grained Iterative Attention Network for TemporalLanguage Localization in Videos
• DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion System
• Reduced Order Modeling with Shallow Recurrent Decoder Networks
• Machine Speech Chain with One-shot Speaker Adaptation
• Generating Black Metal and Math Rock: Beyond Bach, Beethoven, and Beatles
• Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records
• Learning audio sequence representations for acoustic event classification
• Dual-interest Factorization-heads Attention for Sequential Recommendation
• Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks
• Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network
• Visual Text Correction
• Reduced-Gate Convolutional LSTM Using Predictive Coding for Spatiotemporal Prediction
• RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification
• A Comprehensive Survey of Deep Learning for Image Captioning
• Road Segmentation Using CNN with GRU
• Graph Deconvolutional Generation
• EmpDG: Multiresolution Interactive Empathetic Dialogue Generation
• An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms
• TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
• MA-DST: Multi-Attention Based Scalable Dialog State Tracking
• Deep Learning Based Energy Disaggregation and On/Off Detection of Household Appliances
• A Comparison of deep learning methods for environmental sound
• Incorporating Discriminator in Sentence Generation: a Gibbs Sampling Method
• A Time-Temperature Dataset for the Strawberry Cold Chain Across Multiple Shipments and Locations
• Multi-level Gated Recurrent Neural Network for Dialog Act Classification
• T-GSA: Transformer with Gaussian-weighted self-attention for speech enhancement
• ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
• An Integrated Multi-Time-Scale Modeling for Solar Irradiance Forecasting Using Deep Learning
• Making History Matter: History-Advantage Sequence Training for Visual Dialog
• Code Attention: Translating Code to Comments by Exploiting Domain Features
• Human Action Forecasting by Learning Task Grammars
• Representation Stability as a Regularizer for Improved Text Analytics Transfer Learning
• Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer
• DeepTurbo: Deep Turbo Decoder
• A GRU-based Encoder-Decoder Approach with Attention for Online Handwritten Mathematical Expression Recognition
• An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
• Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
• Adversarial Resilience Learning - Towards Systemic Vulnerability Analysis for Large and Complex Systems
• Sequence to Sequence Learning for Optical Character Recognition
• Connecting the Dots Between MLE and RL for Sequence Prediction
• MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning
• Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
• Deep Learning-Based Detection for Marker Codes over Insertion and Deletion Channels
• NAC-TCN: Temporal Convolutional Networks with Causal Dilated Neighborhood Attention for Emotion Understanding
• A Deep Prediction Network for Understanding Advertiser Intent and Satisfaction
• Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data
• Unbounded cache model for online language modeling with open vocabulary
• MSSTNet: A Multi-Scale Spatio-Temporal CNN-Transformer Network for Dynamic Facial Expression Recognition
• Toward a Period-Specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts
• Top-K Off-Policy Correction for a REINFORCE Recommender System
• Activity-aware Human Mobility Prediction with Hierarchical Graph Attention Recurrent Network
• Sentiment Analysis for Sinhala Language using Deep Learning Techniques
• Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis
• An Offset-Free Nonlinear MPC scheme for systems learned by Neural NARX models
• Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy
• Exploiting long-term temporal dynamics for video captioning
• Deep Learning for Network Traffic Classification
• Sequential Dual Deep Learning with Shape and Texture Features for Sketch Recognition
• Neural Machine Translation with Word Predictions
• DenseRAN for Offline Handwritten Chinese Character Recognition
• Locate then Segment: A Strong Pipeline for Referring Image Segmentation
• Beam Search with Bidirectional Strategies for Neural Response Generation
• Neural Tensor Factorization
• Long Short-Term Transformer for Online Action Detection
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators
• T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval
• In Conclusion Not Repetition: Comprehensive Abstractive Summarization With Diversified Attention Based On Determinantal Point Processes
• Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs
• Deep Neural Network Based Relation Extraction: An Overview
• Emergent Communication Pretraining for Few-Shot Machine Translation
• Code-switched inspired losses for generic spoken dialog representations
• Spatial-Temporal Self-Attention Network for Flow Prediction
• Interpretable Multi-Step Reasoning with Knowledge Extraction on Complex Healthcare Question Answering
• Convolutional Residual Memory Networks
• Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization
• Can physical information aid the generalization ability of Neural Networks for hydraulic modeling?
• Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging
• A Dataset Independent Set of Baselines for Relation Prediction in Argument Mining
• Predicting Multiple ICD-10 Codes from Brazilian-Portuguese Clinical Notes
• Transformer Based Reinforcement Learning For Games
• Improving EEG based Continuous Speech Recognition
• A Heterogeneous Dynamical Graph Neural Networks Approach to Quantify Scientific Impact
• Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Hemodynamic Management in Sepsis Patients
• Grammatical Error Correction with Neural Reinforcement Learning
• Towards Bidirectional Hierarchical Representations for Attention-Based Neural Machine Translation
• Language Style Transfer from Sentences with Arbitrary Unknown Styles
• GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
• Probabilistic Time Series Forecasting with Implicit Quantile Networks
• A Neural Network Approach to Joint Modeling Social Networks and Mobile Trajectories
• On the Generation of Medical Dialogues for COVID-19
• Multistep Speed Prediction on Traffic Networks: A Graph Convolutional Sequence-to-Sequence Learning Approach with Attention Mechanism
• Sequence-to-Sequence Forecasting-aided State Estimation for Power Systems
• Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet
• Vehicular Intrusion Detection System for Controller Area Network: A Comprehensive Survey and Evaluation
• Deep Learning for Human Locomotion Analysis in Lower-Limb Exoskeletons: A Comparative Study
• Contrastive Learning of Emoji-based Representations for Resource-Poor Languages
• Polyphonic audio tagging with sequentially labelled data using CRNN with learnable gated linear units
• Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos
• Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?
• Serving Recurrent Neural Networks Efficiently with a Spatial Accelerator
• The CORSMAL benchmark for the prediction of the properties of containers
• State-Regularized Recurrent Neural Networks
• Conditional Driving from Natural Language Instructions
• Improved Cardinality Estimation by Learning Queries Containment Rates
• False News Detection on Social Media
• On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions
• Precision Highway for Ultra Low-Precision Quantization
• Recurrent Neural Networks for Fuzz Testing Web Browsers
• LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing
• Spatial-Channel Transformer Network for Trajectory Prediction on the Traffic Scenes
• Author2Vec: A Framework for Generating User Embedding
• Automated Theorem Proving in Intuitionistic Propositional Logic by Deep Reinforcement Learning
• A Time Attention based Fraud Transaction Detection Framework
• Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots
• Understanding Dataset Design Choices for Multi-hop Reasoning
• Associated Spatio-Temporal Capsule Network for Gait Recognition
• Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records
• Asymmetrical Bi-RNN for pedestrian trajectory encoding
• Can LSTM Learn to Capture Agreement? The Case of Basque
• Natural Language Generation with Neural Variational Models
• Deep neural networks for emotion recognition combining audio and transcripts
• Kronecker Recurrent Units
• Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog
• Improving Botnet Detection with Recurrent Neural Network and Transfer Learning
• Multi-modal Machine Learning for Vehicle Rating Predictions Using Image, Text, and Parametric Data
• Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
• Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks
• Sequence Modeling using Gated Recurrent Neural Networks
• Learning language through pictures
• Unsupervised Features Extraction for Binary Similarity Using Graph Embedding Neural Networks
• Simplified Minimal Gated Unit Variations for Recurrent Neural Networks
• Evaluating KGR10 Polish word embeddings in the recognition of temporal expressions using BiLSTM-CRF
• Risk management with machine-learning-based algorithms
• SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning
• Learning Hierarchical Representations of Electronic Health Records for Clinical Outcome Prediction
• Classification-based RNN machine translation using GRUs
• Hyperbolic Interaction Model For Hierarchical Multi-Label Classification
• Weakly Supervised Energy-Based Learning for Action Segmentation
• Development and Comparative Analysis of Machine Learning Models for Hypoxemia Severity Triage in CBRNE Emergency Scenarios Using Physiological and Demographic Data from Medical-Grade Devices
• Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling
• Emotions are Universal: Learning Sentiment Based Representations of Resource-Poor Languages using Siamese Networks
• Recurrent Neural Network based Part-of-Speech Tagger for Code-Mixed Social Media Text
• Kalman Filtering Attention for User Behavior Modeling in CTR Prediction
• Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• Deep Sequence Models for Text Classification Tasks
• An attention-based Bi-GRU-CapsNet model for hypernymy detection between compound entities
• Breaking the Activation Function Bottleneck through Adaptive Parameterization
• Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos
• SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
• Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments
• MAST: A Memory-Augmented Self-supervised Tracker
• Interpretable Visual Question Answering by Reasoning on Dependency Trees
• ACtuAL: Actor-Critic Under Adversarial Learning
• Convolutional Mixture Density Recurrent Neural Network for Predicting User Location with WiFi Fingerprints
• Learning Cross-modal Context Graph for Visual Grounding
• Learning Heuristics for Quantified Boolean Formulas through Deep Reinforcement Learning
• Collaborative Three-Stream Transformers for Video Captioning
• MaIL: A Unified Mask-Image-Language Trimodal Network for Referring Image Segmentation
• HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving
• Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis
• SenGen: Sentence Generating Neural Variational Topic Model
• Pedestrian Motion State Estimation From 2D Pose
• Byte-based Language Identification with Deep Convolutional Networks
• Visually Grounded Word Embeddings and Richer Visual Features for Improving Multimodal Neural Machine Translation
• Advancing Vietnamese Visual Question Answering with Transformer and Convolutional Integration
• Visual Acuity Prediction on Real-Life Patient Data Using a Machine Learning Based Multistage System
• Adding Attentiveness to the Neurons in Recurrent Neural Networks
• Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments
• Recognizing Micro-Expression in Video Clip with Adaptive Key-Frame Mining
• All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization
• Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt
• Explainable Enterprise Credit Rating via Deep Feature Crossing Network
• Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning
• Different Absorption from the Same Sharing: Sifted Multi-task Learning for Fake News Detection
• An Edge-Cloud Integrated Framework for Flexible and Dynamic Stream Analytics
• A Simple LSTM model for Transition-based Dependency Parsing
• Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification
• Learning Forward Reuse Distance
• The NES Music Database: A multi-instrumental dataset with expressive performance attributes
• Better Sign Language Translation with STMC-Transformer
• Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality
• Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement
• Heterogeneous Data Fusion Considering Spatial Correlations using Graph Convolutional Networks and its Application in Air Quality Prediction
• Better Text Understanding Through Image-To-Text Transfer
• Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences
• Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction
• Frost Prediction Using Machine Learning Methods in Fars Province
• An End-to-End Network for Generating Social Relationship Graphs
• Neural Arithmetic Expression Calculator
• Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
• Syntactically Informed Text Compression with Recurrent Neural Networks
• A Bi-directional Transformer for Musical Chord Recognition
• HOI-aware Adaptive Network for Weakly-supervised Action Segmentation
• STAN: Spatio-Temporal Attention Network for Pandemic Prediction Using Real World Evidence
• Recurrent Neural Networks for anomaly detection in the Post-Mortem time series of LHC superconducting magnets
• Storytelling of Photo Stream with Bidirectional Multi-thread Recurrent Neural Network
• iCapsNets: Towards Interpretable Capsule Networks for Text Classification
• Inspecting and Interacting with Meaningful Music Representations using VAE
• Deep Learning in Information Security
• CNN Is All You Need
• Variational Bi-LSTMs
• Regularizing Towards Permutation Invariance in Recurrent Models
• Interactive Video Corpus Moment Retrieval using Reinforcement Learning
• End-to-End Video Classification with Knowledge Graphs
• Sequential Attention GAN for Interactive Image Editing
• PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers
• Molecular De Novo Design through Deep Reinforcement Learning
• Attention and Localization based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging
• Symbolic inductive bias for visually grounded learning of spoken language
• Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
• Emergent Computations in Trained Artificial Neural Networks and Real Brains
• Spatio-Temporal Hybrid Graph Convolutional Network for Traffic Forecasting in Telecommunication Networks
• Review Helpfulness Prediction with Embedding-Gated CNN
• UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning
• Churn Intent Detection in Multilingual Chatbot Conversations and Social Media
• ADL-MVDR: All deep learning MVDR beamformer for target speech separation
• Meaningful Answer Generation of E-Commerce Question-Answering
• A Model-Driven Stack-Based Fully Convolutional Network for Pancreas Segmentation
• Pelican: A Deep Residual Network for Network Intrusion Detection
• Hierarchical Motion Encoder-Decoder Network for Trajectory Forecasting
• Sensitivity - Local Index to Control Chaoticity or Gradient Globally -
• FLEAM: A Federated Learning Empowered Architecture to Mitigate DDoS in Industrial IoT
• Toward Extractive Summarization of Online Forum Discussions via Hierarchical Attention Networks
• Deep Risk Model: A Deep Learning Solution for Mining Latent Risk Factors to Improve Covariance Matrix Estimation
• Video Is Graph: Structured Graph Module for Video Action Recognition
• Botnet Detection Using Recurrent Variational Autoencoder
• QR-MIX: Distributional Value Function Factorisation for Cooperative Multi-Agent Reinforcement Learning
• Interpretation of Deep Temporal Representations by Selective Visualization of Internally Activated Nodes
• Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks
• LadRa-Net: Locally-Aware Dynamic Re-read Attention Net for Sentence Semantic Matching
• Learning representations for multivariate time series with missing data using Temporal Kernelized Autoencoders
• Enhancing Extractive Text Summarization with Topic-Aware Graph Neural Networks
• Multi-modality Sensor Data Classification with Selective Attention
• Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
• Bilinear Graph Networks for Visual Question Answering
• Topic-Guided Abstractive Text Summarization: a Joint Learning Approach
• ECAS-ML: Edge Computing Assisted Adaptation Scheme with Machine Learning for HTTP Adaptive Streaming
• How Powerful are Interest Diffusion on Purchasing Prediction: A Case Study of Taocode
• Delving Deeper into the Decoder for Video Captioning
• Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
• DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
• Neural Response Generation with Meta-Words
• Music Artist Classification with Convolutional Recurrent Neural Networks
• Visual Question Answering on 360° Images
• LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval
• The Ant Swarm Neuro-Evolution Procedure for Optimizing Recurrent Networks
• Delhi air quality prediction using LSTM deep learning models with a focus on COVID-19 lockdown
• GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media
• Parallel Extraction of Long-term Trends and Short-term Fluctuation Framework for Multivariate Time Series Forecasting
• Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection
• Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition
• An Attention Mechanism for Answer Selection Using a Combined Global and Local View
• Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series
• Interpretable Crowd Flow Prediction with Spatial-Temporal Self-Attention
• Sequence-to-sequence Models for Small-Footprint Keyword Spotting
• Counterfactual Learning from Human Proofreading Feedback for Semantic Parsing
• Trimming and Improving Skip-thought Vectors
• Predicting small molecules solubilities on endpoint devices using deep ensemble neural networks
• Explainable artificial intelligence for mechanics: physics-informing neural networks for constitutive models
• T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model
• Bridging Imagination and Reality for Model-Based Deep Reinforcement Learning
• Tensor Decomposition for Compressing Recurrent Neural Network
• Tricks from Deep Learning
• Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting
• Distributed Heuristic Multi-Agent Path Finding with Communication
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Working Memory Networks: Augmenting Memory Networks with a Relational Reasoning Module
• Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
• Deep Semi-Supervised Learning with Linguistically Motivated Sequence Labeling Task Hierarchies
• Simplified Long Short-term Memory Recurrent Neural Networks: part III
• Voice Cloning: a Multi-Speaker Text-to-Speech Synthesis Approach based on Transfer Learning
• New Item Consumption Prediction Using Deep Learning
• Text-to-Image Generation with Attention Based Recurrent Neural Networks
• Densely Connected Bidirectional LSTM with Applications to Sentence Classification
• Generalized Zero-shot ICD Coding
• Style Transfer with Time Series: Generating Synthetic Financial Data
• Neural Network for NILM Based on Operational State Change Classification
• DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Range
• Trajectory-based Radical Analysis Network for Online Handwritten Chinese Character Recognition
• Long Short-Term Attention
• Neural Turtle Graphics for Modeling City Road Layouts
• BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN
• Evaluating the Performance of Machine Learning Algorithms in Financial Market Forecasting: A Comprehensive Survey
• Prediction-based One-shot Dynamic Parking Pricing
• Imitating Driver Behavior with Generative Adversarial Networks
• Segmented Graph-Bert for Graph Instance Modeling
• A Survey on Natural Language Video Localization
• Text-guided Attention Model for Image Captioning
• Inter-Patient ECG Classification with Convolutional and Recurrent Neural Networks
• A Heterogeneous Information Network based Cross Domain Insurance Recommendation System for Cold Start Users
• Assessing Language Models with Scaling Properties
• Recurrent Multi-Graph Neural Networks for Travel Cost Prediction
• An Efficient Character-Level Neural Machine Translation
• Driver-Net: Multi-Camera Fusion for Assessing Driver Take-Over Readiness in Automated Vehicles
• PassAI: explainable artificial intelligence algorithm for soccer pass analysis using multimodal information resources
• Recurrent Memory Array Structures
• Estimation of Inter-Sentiment Correlations Employing Deep Neural Network Models
• Sens-BERT: Enabling Transferability and Re-calibration of Calibration Models for Low-cost Sensors under Reference Measurements Scarcity
• Methods for generating and evaluating synthetic longitudinal patient data: a systematic review
• Synthetic Sample Selection via Reinforcement Learning
• Notes on Deep Learning for NLP
• A Fusion Approach for Multi-Frame Optical Flow Estimation
• Multimodal Gait Recognition for Neurodegenerative Diseases
• Speech Recognition with no speech or with noisy speech
• Deep learning in bioinformatics: introduction, application, and perspective in big data era
• Cross-lingual Word Segmentation and Morpheme Segmentation as Sequence Labelling
• Gated Recurrent Unit Based Acoustic Modeling with Future Context
• Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis
• Improving RNN Transducer Modeling for End-to-End Speech Recognition
• Session-based Sequential Skip Prediction via Recurrent Neural Networks
• Trace norm regularization and faster inference for embedded speech recognition RNNs
• AirObject: A Temporally Evolving Graph Embedding for Object Identification
• Multi-view Sentence Representation Learning
• Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together
• Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification
• Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization
• Context-aware demand prediction in bike sharing systems: incorporating spatial, meteorological and calendrical context
• Online Signature Verification using Recurrent Neural Network and Length-normalized Path Signature
• Instance-wise Graph-based Framework for Multivariate Time Series Forecasting
• Estimation of Missing Data in Intelligent Transportation System
• Teaching Machines to Converse
• Visual Storytelling via Predicting Anchor Word Embeddings in the Stories
• Self-boosted Time-series Forecasting with Multi-task and Multi-view Learning
• Scaling Graph-based Deep Learning models to larger networks
• A Precisely Xtreme-Multi Channel Hybrid Approach For Roman Urdu Sentiment Analysis
• CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
• Value-Decomposition Multi-Agent Actor-Critics
• SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation
• Surprisal-Triggered Conditional Computation with Neural Networks
• Combination of Convolutional Neural Network and Gated Recurrent Unit for Energy Aware Resource Allocation
• Predicting Gender by First Name Using Character-level Machine Learning
• Extension of Direct Feedback Alignment to Convolutional and Recurrent Neural Network for Bio-plausible Deep Learning
• Attention Forcing for Sequence-to-sequence Model Training
• UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations
• Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model
• Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies
• Sliding Sequential CVAE with Time Variant Socially-aware Rethinking for Trajectory Prediction
• Neural Pharmacodynamic State Space Modeling
• NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
• Radical analysis network for zero-shot learning in printed Chinese character recognition
• Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks
• A Geometric Perspective on Visual Imitation Learning
• On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers
• A Neural Virtual Anchor Synthesizer based on Seq2Seq and GAN Models
• Unsupervised Document Embedding With CNNs
• Different eigenvalue distributions encode the same temporal tasks in recurrent neural networks
• Autoencoder Regularized Network For Driving Style Representation Learning
• The Referential Reader: A Recurrent Entity Network for Anaphora Resolution
• Reinforced Deep Markov Models With Applications in Automatic Trading
• Differentiable Language Model Adversarial Attacks on Categorical Sequence Classifiers
• Few-shot Generation of Personalized Neural Surrogates for Cardiac Simulation via Bayesian Meta-Learning
• Towards Collaborative Plan Acquisition through Theory of Mind Modeling in Situated Dialogue
• Deformation Flow Based Two-Stream Network for Lip Reading
• Sequential Keystroke Behavioral Biometrics for Mobile User Identification via Multi-view Deep Learning
• Automated Optical Multi-layer Design via Deep Reinforcement Learning
• TextNAS: A Neural Architecture Search Space tailored for Text Representation
• A Deep Learning Approach for Predicting Spatiotemporal Dynamics From Sparsely Observed Data
• HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE
• Frame-To-Frame Consistent Semantic Segmentation
• Comparison of neural network architectures for feature extraction from binary black hole merger waveforms
• Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation
• Neural Logic Reasoning
• Event Detection with Neural Networks: A Rigorous Empirical Evaluation
• XAI-Guided Enhancement of Vegetation Indices for Crop Mapping
• Exploring Different Dimensions of Attention for Uncertainty Detection
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• A novel hybrid methodology of measuring sentence similarity
• Topic Sensitive Neural Headline Generation
• Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
• Multi Task Deep Morphological Analyzer: Context Aware Joint Morphological Tagging and Lemma Prediction
• End-to-End Text Classification via Image-based Embedding using Character-level Networks
• Fusion Recurrent Neural Network
• Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version
• Modeling and Predicting Blood Flow Characteristics through Double Stenosed Artery from CFD simulation using Deep Learning Models
• A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19
• Learning-based Prediction and Uplink Retransmission for Wireless Virtual Reality (VR) Network
• Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme
• Manipulation-skill Assessment from Videos with Spatial Attention Network
• The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification
• Topos and Stacks of Deep Neural Networks
• EEG based Continuous Speech Recognition using Transformers
• Personalized Event Prediction for Electronic Health Records
• Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion
• Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory
• Sequence-Aware Recommender Systems
• Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms
• Highly Fast Text Segmentation With Pairwise Markov Chains
• Linking emotions to behaviors through deep transfer learning
• Graph Neural Lasso for Dynamic Network Regression
• Attention-based Memory Selection Recurrent Network for Language Modeling
• Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms
• DeepCSO: Forecasting of Combined Sewer Overflow at a Citywide Level using Multi-task Deep Learning
• Syntax-Infused Variational Autoencoder for Text Generation
• Recent Progresses in Deep Learning based Acoustic Models (Updated)
• Multi-Graph Decoding for Code-Switching ASR
• A Pluggable Learned Index Method via Sampling and Gap Insertion
• Syntax-Aware Language Modeling with Recurrent Neural Networks
• Mobility-Aware Seamless Handover with MPTCP in Software-Defined HetNets
• Modeling the spatio-temporal dynamics of land use change with recurrent neural networks
• Constrained Variational Autoencoder for improving EEG based Speech Recognition Systems
• Rethinking Skip-thought: A Neighborhood based Approach
• Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms
• Graph Distillation for Action Detection with Privileged Modalities
• Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings
• Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent
• Generating Nontrivial Melodies for Music as a Service
• Spatial Memory for Context Reasoning in Object Detection
• Reading Comprehension using Entity-based Memory Network
• Conversational Question Answering: A Survey
• MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation
• MuFuRU: The Multi-Function Recurrent Unit
• Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition
• A Neural Network Alternative to Non-Negative Audio Models
• End-to-End Radio Traffic Sequence Recognition with Deep Recurrent Neural Networks
• Why and How to Pay Different Attention to Phrase Alignments of Different Intensities
• Empirical Evaluation of RNN Architectures on Sentence Classification Task
• A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts
• Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play
• SAFCAR: Structured Attention Fusion for Compositional Action Recognition
• ADD: Augmented Disentanglement Distillation Framework for Improving Stock Trend Forecasting
• Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
• Evaluating Impact of Social Media Posts by Executives on Stock Prices
• Poisoned Source Code Detection in Code Models
• Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques
• Extreme time extrapolation capabilities and thermodynamic consistency of physics-inspired Neural Networks for the 3D microstructure evolution of materials via Cahn-Hilliard flow
• Contextual Text Embeddings for Twi
• deepSELF: An Open Source Deep Self End-to-End Learning Framework
• Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network
• Recurrent Neural Network-based Model for Accelerated Trajectory Analysis in AIMD Simulations
• Real-Time Forecasting of Dockless Scooter-Sharing Demand: A Spatio-Temporal Multi-Graph Transformer Approach
• Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation
• Word Embedding Algorithms as Generalized Low Rank Models and their Canonical Form
• Will This Idea Spread Beyond Academia? Understanding Knowledge Transfer of Scientific Concepts across Text Corpora
• Automating App Review Response Generation Based on Contextual Knowledge
• What Do Position Embeddings Learn? An Empirical Study of Pre-Trained Language Model Positional Encoding
• Multi-Graph Tensor Networks
• SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning
• CNNs, LSTMs, and Attention Networks for Pathology Detection in Medical Data
• FastLR: Non-Autoregressive Lipreading Model with Integrate-and-Fire
• SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition
• Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems
• Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis
• Interpretable Deep Learning Model for Online Multi-touch Attribution
• Predictively Encoded Graph Convolutional Network for Noise-Robust Skeleton-based Action Recognition
• Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog
• TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation
• Learning to Structure Long-term Dependence for Sequential Recommendation
• Encoding-based Memory Modules for Recurrent Neural Networks
• Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units
• Graph Neural Distance Metric Learning with Graph-Bert
• Deep Autotuner: a Pitch Correcting Network for Singing Performances
• Speech-to-Singing Conversion in an Encoder-Decoder Framework
• On the Discrepancy between Density Estimation and Sequence Generation
• A Tree Architecture of LSTM Networks for Sequential Regression with Missing Data
• Piecewise Linear Units Improve Deep Neural Networks
• Temporal Collaborative Ranking Via Personalized Transformer
• Sensor-Based Estimation of Dim Light Melatonin Onset (DLMO) Using Features of Two Time Scales
• Transfer learning from language models to image caption generators: Better models may not transfer better
• Learning Nonlinear State Space Models with Hamiltonian Sequential Monte Carlo Sampler
• DeepNC: Deep Generative Network Completion
• Relationship-Embedded Representation Learning for Grounding Referring Expressions
• Variational Recurrent Neural Networks for Graph Classification
• Self-Attention Aligner: A Latency-Control End-to-End Model for ASR Using Self-Attention Network and Chunk-Hopping
• Attention Boosted Sequential Inference Model
• Uncertainty-Aware Time-to-Event Prediction using Deep Kernel Accelerated Failure Time Models
• Multi-Task Time Series Forecasting With Shared Attention
• Towards NLP with Deep Learning: Convolutional Neural Networks and Recurrent Neural Networks for Offensive Language Identification in Social Media
• Improving Sentence Representations with Consensus Maximisation
• Graph and Recurrent Neural Network-based Vehicle Trajectory Prediction For Highway Driving
• Sequential modeling of Sessions using Recurrent Neural Networks for Skip Prediction
• GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction
• Predefined Sparseness in Recurrent Sequence Models
• Evaluation of Unsupervised Compositional Representations
• Predicting the time-evolution of multi-physics systems with sequence-to-sequence models
• Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification
• I am Robot: Neuromuscular Reinforcement Learning to Actuate Human Limbs through Functional Electrical Stimulation
• Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition
• High-Quality Vocoding Design with Signal Processing for Speech Synthesis and Voice Conversion
• GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting
• Long Short-Term Memory with Dynamic Skip Connections
• Identifying Non-Control Security-Critical Data through Program Dependence Learning
• Efficient Bitrate Ladder Construction using Transfer Learning and Spatio-Temporal Features
• Mean field theory for deep dropout networks: digging up gradient backpropagation deeply
• UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks
• Language model integration based on memory control for sequence to sequence speech recognition
• Recurrent Value Functions
• On the Generation of Medical Question-Answer Pairs
• Towards Interpretable Multilingual Detection of Hate Speech against Immigrants and Women in Twitter at SemEval-2019 Task 5
• Audio-replay attack detection countermeasures
• SCNet: A Neural Network for Automated Side-Channel Attack
• Event Ticket Price Prediction with Deep Neural Network on Spatial-Temporal Sparse Data
• Phase Retrieval using Expectation Consistent Signal Recovery Algorithm based on Hypernetwork
• UIBert: Learning Generic Multimodal Representations for UI Understanding
• Dispersed Exponential Family Mixture VAEs for Interpretable Text Generation
• ConQueR: Contextualized Query Reduction using Search Logs
• Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning
• Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
• Ensemble Deep Learning on Time-Series Representation of Tweets for Rumor Detection in Social Media
• A GRU-based Mixture Density Network for Data-Driven Dynamic Stochastic Programming
• Efficient Heuristic Generation for Robot Path Planning with Recurrent Generative Model
• Deep Discriminative Feature Learning for Accent Recognition
• Speech Recognition With No Speech Or With Noisy Speech Beyond English
• ATCN: Resource-Efficient Processing of Time Series on Edge
• Deep Time Series Models for Scarce Data
• Gated recurrent units and temporal convolutional network for multilabel classification
• Data-driven Hedging of Stock Index Options via Deep Learning
• QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
• Drug Package Recommendation via Interaction-aware Graph Induction
• Online hyperparameter optimization by real-time recurrent learning
• Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model)
• A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions
• PoseConvGRU: A Monocular Approach for Visual Ego-motion Estimation by Learning
• NELEC at SemEval-2019 Task 3: Think Twice Before Going Deep
• Non-Intrusive Binaural Speech Intelligibility Prediction from Discrete Latent Representations
• Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation
• Enriching Conversation Context in Retrieval-based Chatbots
• Learning State Representations via Retracing in Reinforcement Learning
• Comprehensive Evaluation of Deep Learning Architectures for Prediction of DNA/RNA Sequence Binding Specificities
• A Stock Selection Method Based on Earning Yield Forecast Using Sequence Prediction Models
• On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra-observer Variability in 2D Echocardiography Quality Assessment
• All-In-One: Artificial Association Neural Networks
• Lessons learned in multilingual grounded language learning
• Applying Cyclical Learning Rate to Neural Machine Translation
• Improving EEG based continuous speech recognition using GAN
• Learning Word Sense Embeddings from Word Sense Definitions
• Listen, Look and Deliberate: Visual context-aware speech recognition using pre-trained text-video representations
• Voice Activity Detection in presence of background noise using EEG
• Multi-Language Identification Using Convolutional Recurrent Neural Network
• AI Driven Heterogeneous MEC System with UAV Assistance for Dynamic Environment -- Challenges and Solutions
• Toward 3D Object Reconstruction from Stereo Images
• EgoCoder: Intelligent Program Synthesis with Hierarchical Sequential Neural Network Model
• Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances
• An Ensemble Dialogue System for Facts-Based Sentence Generation
• Character-Based Text Classification using Top Down Semantic Model for Sentence Representation
• Controlling Utterance Length in NMT-based Word Segmentation with Attention
• TEGDetector: A Phishing Detector that Knows Evolving Transaction Behaviors
• Learning to Adaptively Scale Recurrent Neural Networks
• SCR-Graph: Spatial-Causal Relationships based Graph Reasoning Network for Human Action Prediction
• ManifoldNorm: Extending normalizations on Riemannian Manifolds
• When Can Self-Attention Be Replaced by Feed Forward Layers?
• Knowledge-Enriched Visual Storytelling
• Question-Aware Memory Network for Multi-hop Question Answering in Human-Robot Interaction
• GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures
• A Hierarchical Deep Convolutional Neural Network and Gated Recurrent Unit Framework for Structural Damage Detection
• Understanding Chat Messages for Sticker Recommendation in Messaging Apps
• Investigating how well contextual features are captured by bi-directional recurrent neural network models
• MUSE: Multi-Scale Temporal Features Evolution for Knowledge Tracing
• Towards Proactively Forecasting Sentence-Specific Information Popularity within Online News Documents
• Graph-Embedded Multi-Agent Learning for Smart Reconfigurable THz MIMO-NOMA Networks
• KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos
• Cross-Modal Generative Augmentation for Visual Question Answering
• Causal Hidden Markov Model for Time Series Disease Forecasting
• Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning
• Hierarchical Memory Decoding for Video Captioning
• Coarse-grained decomposition and fine-grained interaction for multi-hop question answering
• Low Rank Factorization for Compact Multi-Head Self-Attention
• Discovering Predictable Latent Factors for Time Series Forecasting
• An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters
• Evaluating Text-to-Image Matching using Binary Image Selection (BISON)
• Rewriter-Evaluator Architecture for Neural Machine Translation
• Music Generation with Temporal Structure Augmentation
• Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks
• Linguistically Driven Graph Capsule Network for Visual Question Reasoning
• Memory Augmented Multi-Instance Contrastive Predictive Coding for Sequential Recommendation
• An Interpretable Framework for Drug-Target Interaction with Gated Cross Attention
• Accelerating Recommender Systems via Hardware "scale-in"
• Extractive Summarization of Long Documents by Combining Global and Local Context
• Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity
• Modeling Information Need of Users in Search Sessions
• 3D Human motion anticipation and classification
• Survey: Transformer based Video-Language Pre-training
• Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models
• Tensor Networks for Multi-Modal Non-Euclidean Data
• Neuralizing Efficient Higher-order Belief Propagation
• HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs
• Empirical Autopsy of Deep Video Captioning Frameworks
• SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory
• Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning
• WSRNet: Joint Spotting and Recognition of Handwritten Words
• Instrument-Independent Dastgah Recognition of Iranian Classical Music Using AzarNet
• Dynamic Sequential Graph Learning for Click-Through Rate Prediction
• Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
• Variational Dynamic Mixtures
• Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification
• A Novel Multimodal Music Genre Classifier using Hierarchical Attention and Convolutional Neural Network
• Challenges and Opportunities of Speech Recognition for Bengali Language
• Meta-Embeddings Based On Self-Attention
• Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score
• Memory and attention in deep learning
• NeuroTrainer: An Intelligent Memory Module for Deep Learning Training
• A Data-Driven Approach to Smooth Pitch Correction for Singing Voice in Pop Music
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
• Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Language Data
• Sensor Transformation Attention Networks
• Handling Homographs in Neural Machine Translation
• Deep Fisher Discriminant Learning for Mobile Hand Gesture Recognition
• Neural Article Pair Modeling for Wikipedia Sub-article Matching
• Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition
• MCRM: Mother Compact Recurrent Memory
• Adversarial Decomposition of Text Representation
• Towards Relevance and Sequence Modeling in Language Recognition
• Channel Assignment in Uplink Wireless Communication using Machine Learning Approach
• Multiple Visual-Semantic Embedding for Video Retrieval from Query Sentence
• Deep Learning: Our Miraculous Year 1990-1991
• Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition
• SocialGrid: A TCN-enhanced Method for Online Discussion Forecasting
• Continuous Speech Recognition using EEG and Video
• Amharic-Arabic Neural Machine Translation
• Phonocardiographic Sensing using Deep Learning for Abnormal Heartbeat Detection
• Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data
• Code-Switching Detection with Data-Augmented Acoustic and Language Models
• Speaker Identification using EEG
• Dynamic Knowledge Routing Network For Target-Guided Open-Domain Conversation
• Voice@SRIB at SemEval-2020 Task 9 and 12: Stacked Ensembling method for Sentiment and Offensiveness detection in Social Media
• Improved RAMEN: Towards Domain Generalization for Visual Question Answering
• A Deep Neural Framework for Contextual Affect Detection
• Recurrent Estimation of Distributions
• PR-NN: RNN-based Detection for Coded Partial-Response Channels
• Music Playlist Title Generation: A Machine-Translation Approach
• "Wait, I'm Still Talking!" Predicting the Dialogue Interaction Behavior Using Imagine-Then-Arbitrate Model
• Comparison of RNN Encoder-Decoder Models for Anomaly Detection
• Time Series Deinterleaving of DNS Traffic
• Predictive Precompute with Recurrent Neural Networks
• Continuous Silent Speech Recognition using EEG
• An RNN-Survival Model to Decide Email Send Times
• An Optimized and Energy-Efficient Parallel Implementation of Non-Iteratively Trained Recurrent Neural Networks
• Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
• A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph
• DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
• Asset Price Forecasting using Recurrent Neural Networks
• FallDeF5: A Fall Detection Framework Using 5G-based Deep Gated Recurrent Unit Networks
• A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems
• Assessing the Memory Ability of Recurrent Neural Networks
• Domain Wall Leaky Integrate-and-Fire Neurons with Shape-Based Configurable Activation Functions
• Advances in Collaborative Filtering and Ranking
• Detecting Potential Topics In News Using BERT, CRF and Wikipedia
• Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data
• Improving Neuroevolution Using Island Extinction and Repopulation
• Deep Attention-based Representation Learning for Heart Sound Classification
• Gender Prediction from Tweets: Improving Neural Representations with Hand-Crafted Features
• Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization
• Recursive Least Squares Based Refinement Network for the Rollout Trajectory Prediction Methods
• Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
• Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting
• Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations
• TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph
• H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
• Applications of Artificial Intelligence, Machine Learning and related techniques for Computer Networking Systems
• Seq-SG2SL: Inferring Semantic Layout from Scene Graph Through Sequence to Sequence Learning
• A Structured Learning Approach with Neural Conditional Random Fields for Sleep Staging
• Real-time low-resource phoneme recognition on edge devices
• More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching
• A Dual-Staged Context Aggregation Method Towards Efficient End-To-End Speech Enhancement
• Teaching a Massive Open Online Course on Natural Language Processing
• Deep Multi-view Depth Estimation with Predicted Uncertainty
• Hierarchical Hidden Markov Jump Processes for Cancer Screening Modeling
• Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
• Deep Switching State Space Model (DS${}^3$M) for Nonlinear Time Series Forecasting with Regime Switching
• An approach to constraining the Higgs width at the LHC and HL-LHC
• A Semi-Supervised Approach for Low-Resourced Text Generation
• A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement
• Self-supervised Reinforcement Learning with Independently Controllable Subgoals
• Sensor Fusion: Gated Recurrent Fusion to Learn Driving Behavior from Temporal Multimodal Data
• Lets Play Music: Audio-driven Performance Video Generation
• Compositional Structure Learning for Sequential Video Data
• Learning Execution through Neural Code Fusion
• DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs
• Gradients are Not All You Need
• Continual Learning Augmented Investment Decisions
• Mapping high-performance RNNs to in-memory neuromorphic chips
• Towards More Realistic Human-Robot Conversation: A Seq2Seq-based Body Gesture Interaction System
• Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families
• Peak Alignment of Gas Chromatography-Mass Spectrometry Data with Deep Learning
• Click-Based Student Performance Prediction: A Clustering Guided Meta-Learning Approach
• PSTN: Periodic Spatial-temporal Deep Neural Network for Traffic Condition Prediction
• An Empirical Exploration of Deep Recurrent Connections and Memory Cells Using Neuro-Evolution
• TransModality: An End2End Fusion Method with Transformer for Multimodal Sentiment Analysis
• A Context Integrated Relational Spatio-Temporal Model for Demand and Supply Forecasting
• Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks
• Self-supervised Regularization for Text Classification
• Video Summarization via Actionness Ranking
• Intention-Based Lane Changing and Lane Keeping Haptic Guidance Steering System
• Transferable Natural Language Interface to Structured Queries aided by Adversarial Generation
• Cross-Lingual Task-Specific Representation Learning for Text Classification in Resource Poor Languages
• Infrastructure-based End-to-End Learning and Prevention of Driver Failure
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
• Bert4XMR: Cross-Market Recommendation with Bidirectional Encoder Representations from Transformer
• Multi-Scale One-Class Recurrent Neural Networks for Discrete Event Sequence Anomaly Detection
• Many-to-one Recurrent Neural Network for Session-based Recommendation
• Regularized Flexible Activation Function Combinations for Deep Neural Networks
• A Hierarchical User Intention-Habit Extract Network for Credit Loan Overdue Risk Detection
• Speech Recognition using EEG signals recorded using dry electrodes
• Text Classification based on Multi-granularity Attention Hybrid Neural Network
• Towards neural reinforcement learning for large deviations in nonequilibrium systems with memory
• Small Footprint Convolutional Recurrent Networks for Streaming Wakeword Detection
• Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug Design
• End-to-end Models with auditory attention in Multi-channel Keyword Spotting
• Expanding the Text Classification Toolbox with Cross-Lingual Embeddings
• Generating a Machine-learned Equation of State for Fluid Properties
• Dereverberation using joint estimation of dry speech signal and acoustic system
• Variational Sequential Labelers for Semi-Supervised Learning
• Understanding effect of speech perception in EEG based speech recognition systems
• Channel Gain Cartography via Mixture of Experts
• G5: A Universal GRAPH-BERT for Graph-to-Graph Transfer and Apocalypse Learning
• Dimensioning of V2X Services in 5G Networks through Forecast-based Scaling
• Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN
• Predicting resonant properties of plasmonic structures by deep learning
• A Simple Recurrent Unit with Reduced Tensor Product Representations
• A Data-Driven CO2 Leakage Detection Using Seismic Data and Spatial-Temporal Densely Connected Convolutional Neural Networks
• SVP-CF: Selection via Proxy for Collaborative Filtering Data
• Empirical Evaluation of A New Approach to Simplifying Long Short-term Memory (LSTM)
• Predicting Patient State-of-Health using Sliding Window and Recurrent Classifiers
• Zoom-RNN: A Novel Method for Person Recognition Using Recurrent Neural Networks
• Semantic Sentence Embeddings for Paraphrasing and Text Summarization
• Spatio-Temporal Image Boundary Extrapolation
• Building Context-aware Clause Representations for Situation Entity Type Classification
• A framework to compare music generative models using automatic evaluation metrics extended to rhythm
• Intelligent Link Adaptation for Grant-Free Access Cellular Networks: A Distributed Deep Reinforcement Learning Approach
• Optimizing Recurrent Neural Networks Architectures under Time Constraints
• Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference
• Prototypical Recurrent Unit
• Cascaded Mutual Modulation for Visual Reasoning
• Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks
• Accelerating Beam Sweeping in mmWave Standalone 5G New Radios using Recurrent Neural Networks
• Handwriting styles: benchmarks and evaluation metrics
• A Strong and Robust Baseline for Text-Image Matching
• Learning Simpler Language Models with the Differential State Framework
• Multi-Task Learning for Argumentation Mining
• Training Image Selection using Recurrent Neural Networks: An Application in Hydrogeology
• Self-view Grounding Given a Narrated 360° Video
• Bringing Semantic Structures to User Intent Detection in Online Medical Queries
• Deep Chaos Synchronization
• Two-stage training algorithm for AI robot soccer
• Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence
• Learning a Word-Level Language Model with Sentence-Level Noise Contrastive Estimation for Contextual Sentence Probability Estimation
• Weather Analogs with a Machine Learning Similarity Metric for Renewable Resource Forecasting
• LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment
• A Concept Knowledge-Driven Keywords Retrieval Framework for Sponsored Search
• Introducing the Hidden Neural Markov Chain framework
• Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation
• The Role of the Input in Natural Language Video Description
• Edge-Labeling based Directed Gated Graph Network for Few-shot Learning
• HinFlair: pre-trained contextual string embeddings for pos tagging and text classification in the Hindi language
• ArrowGAN : Learning to Generate Videos by Learning Arrow of Time
• Research on Fast Text Recognition Method for Financial Ticket Image
• Pricing spread option with liquidity adjustments
• Hybrid Interest Modeling for Long-tailed Users
• A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect
• R${}^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching
• Research on All-content Text Recognition Method for Financial Ticket Image
• From syntactic structure to semantic relationship: hypernym extraction from definitions by recurrent neural networks using the part of speech information
• Reciprocal Supervised Learning Improves Neural Machine Translation
• TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation
• Improving Clinical Outcome Predictions Using Convolution over Medical Entities with Multimodal Learning
• Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks
• ConFuse: Convolutional Transform Learning Fusion Framework For Multi-Channel Data Analysis
• Template Controllable keywords-to-text Generation
• CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
• DeepFoldit -- A Deep Reinforcement Learning Neural Network Folding Proteins
• Siamese Neural Networks for Class Activity Detection
• Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting
• Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions
• Improving Multi-Party Dialogue Discourse Parsing via Domain Integration
• Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots
• Efficient Modelling Across Time of Human Actions and Interactions
• Equivariant Neural Network for Factor Graphs
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos
• Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding
• Opinion Prediction with User Fingerprinting
• Edge-featured Graph Neural Architecture Search
• Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation
• #StayHome or #Marathon? Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs
• A Temporal Knowledge Graph Completion Method Based on Balanced Timestamp Distribution
• RECOWNs: Probabilistic Circuits for Trustworthy Time Series Forecasting
• Lyapunov-based uncertainty-aware safe reinforcement learning
• Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking
• Neural Search: Learning Query and Product Representations in Fashion E-commerce
• Predicting Different Acoustic Features from EEG and towards direct synthesis of Audio Waveform from EEG
• PocketVAE: A Two-step Model for Groove Generation and Control
• Single Model for Influenza Forecasting of Multiple Countries by Multi-task Learning
• A Topic Guided Pointer-Generator Model for Generating Natural Language Code Summaries
• Recurrently Estimating Reflective Symmetry Planes from Partial Pointclouds
• Contrastive Semantic Similarity Learning for Image Captioning Evaluation with Intrinsic Auto-encoder
• Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
• Building Intelligent Autonomous Navigation Agents
• Detection of Consonant Errors in Disordered Speech Based on Consonant-vowel Segment Embedding
• CMF: Cascaded Multi-model Fusion for Referring Image Segmentation
• Robust Unsupervised Multi-Object Tracking in Noisy Environments
• Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
• SGE net: Video object detection with squeezed GRU and information entropy map
• Distributed Learning and its Application for Time-Series Prediction
• DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching
• Pedestrian Tracking with Gated Recurrent Units and Attention Mechanisms
• Conversational Fashion Image Retrieval via Multiturn Natural Language Feedback
• Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
• Grounding Complex Navigational Instructions Using Scene Graphs
• Neural Auto-Curricula
• Graph Convolutional Memory using Topological Priors
• A Coarse to Fine Question Answering System based on Reinforcement Learning
• CITIES: Contextual Inference of Tail-Item Embeddings for Sequential Recommendation
• Joint Forecasting and Interpolation of Graph Signals Using Deep Learning
• A brain basis of dynamical intelligence for AI and computational neuroscience
• Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation
• Neuroevolutionary Transfer Learning of Deep Recurrent Neural Networks through Network-Aware Adaptation
• Iterative Edit-Based Unsupervised Sentence Simplification
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection
• Efficient text generation of user-defined topic using generative adversarial networks
• Clustering Vietnamese Conversations From Facebook Page To Build Training Dataset For Chatbot
• Development and Validation of a Novel Prognostic Model for Predicting AMD Progression Using Longitudinal Fundus Images
• Detecting the Insider Threat with Long Short Term Memory (LSTM) Neural Networks
• Deep Learning based, end-to-end metaphor detection in Greek language with Recurrent and Convolutional Neural Networks
• A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification
• Graph Wasserstein Correlation Analysis for Movie Retrieval
• Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers
• TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
• Modeling Irregular Astronomical Time Series with Neural Stochastic Delay Differential Equations
• Enhancing Reinforcement Learning Through Guided Search
• Comprehensive forecasting based analysis using stacked stateless and stateful Gated Recurrent Unit models
• Forecasting with Multiple Seasonality
• Connecting Web Event Forecasting with Anomaly Detection: A Case Study on Enterprise Web Applications Using Self-Supervised Neural Networks
• Automatic deep learning for trend prediction in time series data
• Gated Res2Net for Multivariate Time Series Analysis
• Modeling Dyadic Conversations for Personality Inference
• From Cities to Series: Complex Networks and Deep Learning for Improved Spatial and Temporal Analytics*
• An Experimental Study of Weight Initialization and Weight Inheritance Effects on Neuroevolution
• Molecular Attributes Transfer from Non-Parallel Data
• Switching Recurrent Kalman Networks
• Deep Learning based Urban Vehicle Trajectory Analytics
• Spectral Transform Forms Scalable Transformer
• Contrastive Active Inference
• Quantifying the Suicidal Tendency on Social Media: A Survey
• Selective Differential Privacy for Language Modeling
• Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems
• TD-GEN: Graph Generation With Tree Decomposition
• Recurrent Neural Networks to automate Quality assessment of Software Requirements
• T-EMDE: Sketching-based global similarity for cross-modal retrieval
• SHARE: a System for Hierarchical Assistive Recipe Editing
• Label-Conditioned Next-Frame Video Generation with Neural Flows
• A Probabilistic Framework for Learning Domain Specific Hierarchical Word Embeddings
• Learning State Representations from Random Deep Action-conditional Predictions
• Learning Preferences and Demands in Visual Recommendation
• Reinforcement Learning of Implicit and Explicit Control Flow in Instructions
• Polynomial Trajectory Predictions for Improved Learning Performance
• Parallel Interactive Networks for Multi-Domain Dialogue State Generation
• Graph Deep Factors for Forecasting
• Point Cloud Processing via Recurrent Set Encoding
• CryptoGRU: Low Latency Privacy-Preserving Text Analysis With GRU
• Matrix Engines for High Performance Computing:A Paragon of Performance or Grasping at Straws?
• Efficient Global String Kernel with Random Features: Beyond Counting Substructures
• Modeling Inter-Aspect Dependencies with a Non-temporal Mechanism for Aspect-Based Sentiment Analysis
• BGC: Multi-Agent Group Belief with Graph Clustering
• Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records
• On estimating gaze by self-attention augmented convolutions
• Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization
• Deep or Simple Models for Semantic Tagging? It Depends on your Data [Experiments]
• Diagnosis and Analysis of Celiac Disease and Environmental Enteropathy on Biopsy Images using Deep Learning Approaches
• Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach
• CASE: Context-Aware Semantic Expansion
• Character-Aware Attention-Based End-to-End Speech Recognition
• Modeling Musical Structure with Artificial Neural Networks
• Visual Question Answering Using Semantic Information from Image Descriptions
• Temporally Folded Convolutional Neural Networks for Sequence Forecasting
• Edge-assisted Viewport Adaptive Scheme for real-time Omnidirectional Video transmission
• Parallel Intent and Slot Prediction using MLB Fusion
• Read Beyond the Lines: Understanding the Implied Textual Meaning via a Skim and Intensive Reading Model
• Longitudinal Pooling & Consistency Regularization to Model Disease Progression from MRIs
• Predict your Click-out: Modeling User-Item Interactions and Session Actions in an Ensemble Learning Fashion
• Automating App Review Response Generation
• Text Classification with Lexicon from PreAttention Mechanism
• Time-weighted Attentional Session-Aware Recommender System
• Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses
• Spoken Speech Enhancement using EEG
• MEETING BOT: Reinforcement Learning for Dialogue Based Meeting Scheduling
• Sub-Spectrogram Segmentation for Environmental Sound Classification via Convolutional Recurrent Neural Network and Score Level Fusion
• Multiple Generative Models Ensemble for Knowledge-Driven Proactive Human-Computer Dialogue Agent
• Deep Unsupervised Drum Transcription
• Visualizing Semantic Structures of Sequential Data by Learning Temporal Dependencies
• Evaluating Bregman Divergences for Probability Learning from Crowd
• Compositional Network Embedding
• Duration-of-Stay Storage Assignment under Uncertainty
• A Deep Learning Approach for Automotive Radar Interference Mitigation
• Domain-Constrained Advertising Keyword Generation
• Understanding Feature Selection and Feature Memorization in Recurrent Neural Networks
• Sequential Variational Autoencoders for Collaborative Filtering
• Improved Dynamic Memory Network for Dialogue Act Classification with Adversarial Training
• Network Horizon Dynamics I: Qualitative Aspects
• Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
• Modeling Melodic Feature Dependency with Modularized Variational Auto-Encoder
• Semi-supervised acoustic model training for speech with code-switching
• XJTLUIndoorLoc: A New Fingerprinting Database for Indoor Localization and Trajectory Estimation Based on Wi-Fi RSS and Geomagnetic Field
• CanvasGAN: A simple baseline for text to image generation by incrementally patching a canvas
• Using Multi-task and Transfer Learning to Solve Working Memory Tasks
• Recurrent Neural Networks based Obesity Status Prediction Using Activity Data
• Deep Domain Adaptation under Deep Label Scarcity
• Learning short-term past as predictor of human behavior in commercial buildings
• Deep Co-investment Network Learning for Financial Assets
• A recurrent multi-scale approach to RBG-D Object Recognition
• Approximate Distribution Matching for Sequence-to-Sequence Learning
• Exploiting Invertible Decoders for Unsupervised Sentence Representation Learning
• Using Context Information to Enhance Simple Question Answering
• Top-Down Tree Structured Text Generation
• Deep Learning Based Natural Language Processing for End to End Speech Translation
• Learning to Represent Bilingual Dictionaries
• Waveform to Single Sinusoid Regression to Estimate the F0 Contour from Noisy Speech Using Recurrent Deep Neural Networks
• Progressive Spatial Recurrent Neural Network for Intra Prediction
• Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction
• Improving Minimal Gated Unit for Sequential Data
• Target-Guided Open-Domain Conversation
• Learning Longer-term Dependencies via Grouped Distributor Unit
• SNU_IDS at SemEval-2018 Task 12: Sentence Encoder with Contextualized Vectors for Argument Reasoning Comprehension
• Recurrent Existence Determination Through Policy Optimization
• Incorporating Chinese Radicals Into Neural Machine Translation: Deeper Than Character Level
• Incremental Learning from Scratch for Task-Oriented Dialogue Systems
• Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
• Latent Multi-Criteria Ratings for Recommendations
• Neural Image Captioning
• Two-stream Spatiotemporal Feature for Video QA Task
• Conversational Help for Task Completion and Feature Discovery in Personal Assistants
• Broad Learning for Healthcare
• Click-Through Rate Prediction with the User Memory Network
• The emergent algebraic structure of RNNs and embeddings in NLP
• On the difficulty of a distributional semantics of spoken language
• CRNN: A Joint Neural Network for Redundancy Detection
• Content-Based Table Retrieval for Web Queries
• Towards the Improvement of Automated Scientific Document Categorization by Deep Learning
• SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
• Learning to Organize Knowledge and Answer Questions with N-Gram Machines
• Topical Behavior Prediction from Massive Logs
• Network of Recurrent Neural Networks
• Dual Attention Network for Product Compatibility and Function Satisfiability Analysis
• Compositional Sentence Representation from Character within Large Context Text
• Skip-Thought Memory Networks
• OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas
• An Empirical Framework for Domain Generalization in Clinical Settings