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.

Presented in NIPS 2014 Deep Learning and Representation Learning Workshop

References in corpus (2)

• Theano: new features and speed improvements
• Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription

Cited by in corpus (856)

• Comparative Study of CNN and RNN for Natural Language Processing
• Skip-Thought Vectors
• Deep Learning for Time Series Anomaly Detection: A Survey
• SpeechBrain: A General-Purpose Speech Toolkit
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Understanding Neural Networks through Representation Erasure
• Image and Video Compression with Neural Networks: A Review
• Artificial neural networks for neuroscientists: A primer
• Deep Voice: Real-time Neural Text-to-Speech
• DyNet: The Dynamic Neural Network Toolkit
• A Comprehensive Survey on Deep Graph Representation Learning
• 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
• Working Memory Connections for LSTM
• Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities
• A Gated Recurrent Unit Approach to Bitcoin Price Prediction
• LipNet: End-to-End Sentence-level Lipreading
• 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
• Visual Entailment: A Novel Task for Fine-Grained Image Understanding
• Social Interactions for Autonomous Driving: A Review and Perspectives
• How Much Can CLIP Benefit Vision-and-Language Tasks?
• VLT: Vision-Language Transformer and Query Generation for Referring Segmentation
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• Deep Learning and Its Applications to Machine Health Monitoring: A Survey
• 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)
• Heterogeneous Task Offloading and Resource Allocations via Deep Recurrent Reinforcement Learning in Partial Observable Multi-Fog Networks
• 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
• Neural Machine Translation and Sequence-to-sequence Models: A Tutorial
• 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
• DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
• Generating and designing DNA with deep generative models
• Compressing Recurrent Neural Network with Tensor Train
• MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
• STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction
• Learning to Generate Questions by Learning What not to Generate
• Gait Recognition Based on Deep Learning: A Survey
• ATRank: An Attention-Based User Behavior Modeling Framework for Recommendation
• 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
• Flexible statistical inference for mechanistic models of neural dynamics
• Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
• Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
• R-Transformer: Recurrent Neural Network Enhanced Transformer
• From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities
• Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities
• THUMT: An Open Source Toolkit for Neural Machine Translation
• Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
• Low-Resource Knowledge-Grounded Dialogue Generation
• Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers
• A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions
• Memory-augmented Dense Predictive Coding for Video Representation Learning
• Thermodynamically Consistent Machine-Learned Internal State Variable Approach for Data-Driven Modeling of Path-Dependent Materials
• DepressionNet: A Novel Summarization Boosted Deep Framework for Depression Detection on Social Media
• A Novel Deep Neural Network Architecture for Real-Time Water Demand Forecasting
• Machine Learning vs Statistical Methods for Time Series Forecasting: Size Matters
• Survey on Machine Learning for Traffic-Driven Service Provisioning in Optical Networks
• Recurrent Neural Networks for Time Series Forecasting
• Application of generative autoencoder in de novo molecular design
• LFADS - Latent Factor Analysis via Dynamical Systems
• SleePyCo: Automatic Sleep Scoring with Feature Pyramid and Contrastive Learning
• Table Structure Extraction with Bi-directional Gated Recurrent Unit Networks
• Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load
• Query Focused Abstractive Summarization: Incorporating Query Relevance, Multi-Document Coverage, and Summary Length Constraints into seq2seq Models
• Unsupervised Deep Learning for IoT Time Series
• Instance-Specific Feature Propagation for Referring Segmentation
• Effective Quantization Methods for Recurrent Neural Networks
• Semantic Tagging with Deep Residual Networks
• Machine learning for music genre: multifaceted review and experimentation with audioset
• Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction
• Automatic Detection of Malware-Generated Domains with Recurrent Neural Models
• Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets
• Neural Networks for Text Correction and Completion in Keyboard Decoding
• Predicting Temporal Sets with Deep Neural Networks
• Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
• Delta Descriptors: Change-Based Place Representation for Robust Visual Localization
• EKT: Exercise-aware Knowledge Tracing for Student Performance Prediction
• Graph-MLP: Node Classification without Message Passing in Graph
• Deep Learning for Sentiment Analysis : A Survey
• Graph-based Neural Multi-Document Summarization
• 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
• Advances in Quantum Deep Learning: An Overview
• Molecular Generation with Recurrent Neural Networks (RNNs)
• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• Automated Audio Captioning: An Overview of Recent Progress and New Challenges
• Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies
• Maybe Deep Neural Networks are the Best Choice for Modeling Source Code
• Motif-based Graph Self-Supervised Learning for Molecular Property Prediction
• Model-Based Reinforcement Learning with Adversarial Training for Online Recommendation
• Geometric deep learning for computational mechanics Part II: Graph embedding for interpretable multiscale plasticity
• Neural Information Retrieval: A Literature Review
• Direction-Oriented Visual-semantic Embedding Model for Remote Sensing Image-text Retrieval
• 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
• Delta Networks for Optimized Recurrent Network Computation
• Artificial Intelligence and Deep Learning Algorithms for Epigenetic Sequence Analysis: A Review for Epigeneticists and AI Experts
• LightRNN: Memory and Computation-Efficient Recurrent Neural Networks
• Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems
• Message-Passing Neural Networks Learn Little's Law
• Speaker Adaptation for Attention-Based End-to-End Speech Recognition
• Toward automatic generation of control structures for process flow diagrams with large language models
• Uncertainty-Aware Probabilistic Graph Neural Networks for Road-Level Traffic Accident Prediction
• Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning
• Ray Interference: a Source of Plateaus in Deep Reinforcement Learning
• AdaRNN: Adaptive Learning and Forecasting of Time Series
• Exploiting Positional Information for Session-based Recommendation
• Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings
• MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction
• Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark
• 3G structure for image caption generation
• Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
• Latent Attention For If-Then Program Synthesis
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Recurrent neural networks and transfer learning for elasto-plasticity in woven composites
• Exploring Self-Supervised Representation Ensembles for COVID-19 Cough Classification
• Network On Network for Tabular Data Classification in Real-world Applications
• Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
• Deep Conversational Recommender in Travel
• SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction
• Autoregressive Coefficients based Intelligent Protection of Transmission Lines Connected to Type-3 Wind Farms
• Aspect Category Detection via Topic-Attention Network
• Conversational Emotion Analysis via Attention Mechanisms
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• Multi-modal gated recurrent units for image description
• An End-to-End Architecture for Keyword Spotting and Voice Activity Detection
• Explicit Time Embedding Based Cascade Attention Network for Information Popularity Prediction
• Predicting Drivers' Route Trajectories in Last-Mile Delivery Using A Pair-wise Attention-based Pointer Neural Network
• UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers
• Classification of Handwritten Names of Cities and Handwritten Text Recognition using Various Deep Learning Models
• Cortical microcircuits as gated-recurrent neural networks
• Multivariate Time-series Anomaly Detection via Graph Attention Network
• Discrete Event, Continuous Time RNNs
• Gated Recurrent Neural Tensor Network
• R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting
• SVFAP: Self-supervised Video Facial Affect Perceiver
• DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases
• AMPNet: Asynchronous Model-Parallel Training for Dynamic Neural Networks
• A multi-task learning model for malware classification with useful file access pattern from API call sequence
• Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
• Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
• Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
• Speaker Diarization with Lexical Information
• RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music
• Beyond Greedy Search: Tracking by Multi-Agent Reinforcement Learning-based Beam Search
• Keyword Decisions in Sponsored Search Advertising: A Literature Review and Research Agenda
• E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction
• Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural Networks
• Modeling Multi-aspect Preferences and Intents for Multi-behavioral Sequential Recommendation
• Neural Machine Translation with Supervised Attention
• Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
• Composite Motion Learning with Task Control
• Understanding Hidden Memories of Recurrent Neural Networks
• Leveraging Multilingual Transformers for Hate Speech Detection
• Machine Learning in High Energy Physics: A review of heavy-flavor jet tagging at the LHC
• Uncertainty-Aware Reliable Text Classification
• Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks
• Transcribing Content from Structural Images with Spotlight Mechanism
• A machine learning-based viscoelastic-viscoplastic model for epoxy nanocomposites with moisture content
• Deep Sequence Modeling: Development and Applications in Asset Pricing
• Causal Navigation by Continuous-time Neural Networks
• Image-Conditioned Graph Generation for Road Network Extraction
• VoiceFixer: Toward General Speech Restoration with Neural Vocoder
• Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
• Unsupervised temporal context learning using convolutional neural networks for laparoscopic workflow analysis
• NUVA: A Naming Utterance Verifier for Aphasia Treatment
• Query-Based Abstractive Summarization Using Neural Networks
• Named Entity Recognition with stack residual LSTM and trainable bias decoding
• Explanation as a Defense of Recommendation
• Continuous Gesture Recognition from sEMG Sensor Data with Recurrent Neural Networks and Adversarial Domain Adaptation
• Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
• Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning
• From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning
• Neural Language Generation: Formulation, Methods, and Evaluation
• Neural-PIM: Efficient Processing-In-Memory with Neural Approximation of Peripherals
• Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech Recognition
• Algorithmic Composition of Melodies with Deep Recurrent Neural Networks
• Large-Scale User Modeling with Recurrent Neural Networks for Music Discovery on Multiple Time Scales
• Embodied Visual Recognition
• A Survey on Principles, Models and Methods for Learning from Irregularly Sampled Time Series
• Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task
• Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation
• A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes
• Basis Pursuit Denoising via Recurrent Neural Network Applied to Super-resolving SAR Tomography
• Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition
• Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models
• Robust constrained nonlinear Model Predictive Control with Gated Recurrent Unit model -- Extended version
• Label Dependent Attention Model for Disease Risk Prediction Using Multimodal Electronic Health Records
• Uncertainty on Asynchronous Time Event Prediction
• Exploration of Neural Machine Translation in Autoformalization of Mathematics in Mizar
• Towards Conversational Recommendation over Multi-Type Dialogs
• Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study
• Highrisk Prediction from Electronic Medical Records via Deep Attention Networks
• Review of end-to-end speech synthesis technology based on deep learning
• STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing
• Comparison of Deep learning models on time series forecasting : a case study of Dissolved Oxygen Prediction
• Learning to Count Isomorphisms with Graph Neural Networks
• Federated Learning of N-gram Language Models
• CS-TGN: Community Search via Temporal Graph Neural Networks
• A Novel Ensemble Deep Learning Model for Stock Prediction Based on Stock Prices and News
• Sequential Attention Source Identification Based on Feature Representation
• Representation-Aggregation Networks for Segmentation of Multi-Gigapixel Histology Images
• Quo Vadis: Hybrid Machine Learning Meta-Model based on Contextual and Behavioral Malware Representations
• Seq2Emo for Multi-label Emotion Classification Based on Latent Variable Chains Transformation
• Collaborative Visual Navigation
• Sound Event Detection with Sequentially Labelled Data Based on Connectionist Temporal Classification and Unsupervised Clustering
• Recent Advances and Trends in Multimodal Deep Learning: A Review
• Fully Transformer-Equipped Architecture for End-to-End Referring Video Object Segmentation
• On the Benefit of Combining Neural, Statistical and External Features for Fake News Identification
• A machine learning and feature engineering approach for the prediction of the uncontrolled re-entry of space objects
• A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting
• Multichannel CNN with Attention for Text Classification
• Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning
• SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders
• Improving Background Based Conversation with Context-aware Knowledge Pre-selection
• AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting
• 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
• Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction
• Improving Interpretability of Deep Neural Networks with Semantic Information
• Deep Audio-Visual Learning: A Survey
• RMIX: Learning Risk-Sensitive Policies for Cooperative Reinforcement Learning Agents
• Modelling Sentence Pairs with Tree-structured Attentive Encoder
• The Statistical Recurrent Unit
• Are Emojis Predictable?
• Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark
• Virtual-to-Real-World Transfer Learning for Robots on Wilderness Trails
• From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning
• A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
• Aspect-Based Relational Sentiment Analysis Using a Stacked Neural Network Architecture
• End-to-end Learning for 3D Facial Animation from Raw Waveforms of Speech
• Context-aware Biaffine Localizing Network for Temporal Sentence Grounding
• SeqNAS: Neural Architecture Search for Event Sequence Classification
• A Static and Dynamic Attention Framework for Multi Turn Dialogue Generation
• HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition
• Style Imitation and Chord Invention in Polyphonic Music with Exponential Families
• Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning
• Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
• Separating Answers from Queries for Neural Reading Comprehension
• Monotonic Neural Ordinary Differential Equation: Time-series Forecasting for Cumulative Data
• Context Gates for Neural Machine Translation
• The Winning Solution to the IEEE CIG 2017 Game Data Mining Competition
• Automatic classification of eclipsing binary stars using deep learning methods
• Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
• Exploring the Landscape of Ubiquitous In-home Health Monitoring: A Comprehensive Survey
• Robust Trajectory Forecasting for Multiple Intelligent Agents in Dynamic Scene
• Incremental Dense Reconstruction from Monocular Video with Guided Sparse Feature Volume Fusion
• 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
• LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
• Style Example-Guided Text Generation using Generative Adversarial Transformers
• PharmMT: A Neural Machine Translation Approach to Simplify Prescription Directions
• Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks
• Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network
• Dual-interest Factorization-heads Attention for Sequential Recommendation
• Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters
• Machine Learning for Detecting Data Exfiltration: A Review
• Large-scale weakly supervised audio classification using gated convolutional neural network
• Reduced Order Modeling with Shallow Recurrent Decoder Networks
• Efficient Convolutional Neural Network Training with Direct Feedback Alignment
• Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values
• Bidirectional Recurrent Neural Networks for Medical Event Detection in Electronic Health Records
• SEAL: Segment-wise Extractive-Abstractive Long-form Text Summarization
• A Dual-Stream Recurrence-Attention Network With Global-Local Awareness for Emotion Recognition in Textual Dialog
• Toward Multimodal Model-Agnostic Meta-Learning
• Fine-grained Iterative Attention Network for TemporalLanguage Localization in Videos
• DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion System
• Hardware Accelerator for Multi-Head Attention and Position-Wise Feed-Forward in the Transformer
• ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit
• T-GSA: Transformer with Gaussian-weighted self-attention for speech enhancement
• Enabling My Robot To Play Pictionary : Recurrent Neural Networks For Sketch Recognition
• Multi-level Gated Recurrent Neural Network for Dialog Act Classification
• Graph Deconvolutional Generation
• MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning
• Making History Matter: History-Advantage Sequence Training for Visual Dialog
• A GRU-based Encoder-Decoder Approach with Attention for Online Handwritten Mathematical Expression Recognition
• A Comparison of deep learning methods for environmental sound
• A Time-Temperature Dataset for the Strawberry Cold Chain Across Multiple Shipments and Locations
• MA-DST: Multi-Attention Based Scalable Dialog State Tracking
• Human Action Forecasting by Learning Task Grammars
• Code Attention: Translating Code to Comments by Exploiting Domain Features
• RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification
• An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
• DeepTurbo: Deep Turbo Decoder
• Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
• An Offset-Free Nonlinear MPC scheme for systems learned by Neural NARX models
• Convolutional Residual Memory Networks
• Unbounded cache model for online language modeling with open vocabulary
• Sequential Dual Deep Learning with Shape and Texture Features for Sketch Recognition
• Neural Machine Translation with Word Predictions
• Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data
• Spatial-Temporal Self-Attention Network for Flow Prediction
• HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators
• A Deep Prediction Network for Understanding Advertiser Intent and Satisfaction
• Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization
• Interpretable Multi-Step Reasoning with Knowledge Extraction on Complex Healthcare Question Answering
• Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs
• T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval
• Locate then Segment: A Strong Pipeline for Referring Image Segmentation
• Deep Neural Network Based Relation Extraction: An Overview
• Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy
• Sentiment Analysis for Sinhala Language using Deep Learning Techniques
• Beam Search with Bidirectional Strategies for Neural Response Generation
• Code-switched inspired losses for generic spoken dialog representations
• Deep Learning for Network Traffic Classification
• Exploiting long-term temporal dynamics for video captioning
• Toward a Period-Specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts
• MSSTNet: A Multi-Scale Spatio-Temporal CNN-Transformer Network for Dynamic Facial Expression Recognition
• NAC-TCN: Temporal Convolutional Networks with Causal Dilated Neighborhood Attention for Emotion Understanding
• Can physical information aid the generalization ability of Neural Networks for hydraulic modeling?
• Deep Learning-Based Detection for Marker Codes over Insertion and Deletion Channels
• Activity-aware Human Mobility Prediction with Hierarchical Graph Attention Recurrent Network
• Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis
• State-Regularized Recurrent Neural Networks
• Deep Learning for Human Locomotion Analysis in Lower-Limb Exoskeletons: A Comparative Study
• 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
• GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
• Conditional Driving from Natural Language Instructions
• Probabilistic Time Series Forecasting with Implicit Quantile Networks
• Improving EEG based Continuous Speech Recognition
• Convolutional Gated Recurrent Neural Network Incorporating Spatial Features for Audio Tagging
• Differentially Private Multivariate Time Series Forecasting of Aggregated Human Mobility With Deep Learning: Input or Gradient Perturbation?
• Recurrent Neural Networks for Fuzz Testing Web Browsers
• Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos
• Sequence-to-Sequence Forecasting-aided State Estimation for Power Systems
• Towards Bidirectional Hierarchical Representations for Attention-Based Neural Machine Translation
• Vehicular Intrusion Detection System for Controller Area Network: A Comprehensive Survey and Evaluation
• Precision Highway for Ultra Low-Precision Quantization
• Serving Recurrent Neural Networks Efficiently with a Spatial Accelerator
• Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet
• On the Generation of Medical Dialogues for COVID-19
• Transformer Based Reinforcement Learning For Games
• Spatial-Channel Transformer Network for Trajectory Prediction on the Traffic Scenes
• Multi-modal Machine Learning for Vehicle Rating Predictions Using Image, Text, and Parametric Data
• Sequence Modeling using Gated Recurrent Neural Networks
• Understanding Dataset Design Choices for Multi-hop Reasoning
• Improving Botnet Detection with Recurrent Neural Network and Transfer Learning
• Classification-based RNN machine translation using GRUs
• 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
• Evaluating KGR10 Polish word embeddings in the recognition of temporal expressions using BiLSTM-CRF
• Learning language through pictures
• Associated Spatio-Temporal Capsule Network for Gait Recognition
• Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks
• Weakly Supervised Energy-Based Learning for Action Segmentation
• Asymmetrical Bi-RNN for pedestrian trajectory encoding
• Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog
• Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition
• Simplified Minimal Gated Unit Variations for Recurrent Neural Networks
• Recurrent Neural Network based Part-of-Speech Tagger for Code-Mixed Social Media Text
• Deep neural networks for emotion recognition combining audio and transcripts
• Learning Cross-modal Context Graph for Visual Grounding
• Advancing Vietnamese Visual Question Answering with Transformer and Convolutional Integration
• Byte-based Language Identification with Deep Convolutional Networks
• Pedestrian Motion State Estimation From 2D Pose
• Visual Acuity Prediction on Real-Life Patient Data Using a Machine Learning Based Multistage System
• Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• MAST: A Memory-Augmented Self-supervised Tracker
• Regularized Two-Branch Proposal Networks for Weakly-Supervised Moment Retrieval in Videos
• Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification
• Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning
• Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments
• Deep Sequence Models for Text Classification Tasks
• SNAC: Speaker-normalized affine coupling layer in flow-based architecture for zero-shot multi-speaker text-to-speech
• ACtuAL: Actor-Critic Under Adversarial Learning
• SenGen: Sentence Generating Neural Variational Topic Model
• All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization
• Collaborative Three-Stream Transformers for Video Captioning
• A Simple LSTM model for Transition-based Dependency Parsing
• An Edge-Cloud Integrated Framework for Flexible and Dynamic Stream Analytics
• Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt
• Convolutional Mixture Density Recurrent Neural Network for Predicting User Location with WiFi Fingerprints
• HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving
• CNN Is All You Need
• Better Text Understanding Through Image-To-Text Transfer
• Variational Bi-LSTMs
• PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers
• Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction
• An End-to-End Network for Generating Social Relationship Graphs
• A Bi-directional Transformer for Musical Chord Recognition
• Interactive Video Corpus Moment Retrieval using Reinforcement Learning
• Spatio-Temporal Hybrid Graph Convolutional Network for Traffic Forecasting in Telecommunication Networks
• Memory-augmented Adversarial Autoencoders for Multivariate Time-series Anomaly Detection with Deep Reconstruction and Prediction
• Social Scene Understanding: End-to-End Multi-Person Action Localization and Collective Activity Recognition
• Attention and Localization based on a Deep Convolutional Recurrent Model for Weakly Supervised Audio Tagging
• Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality
• Learning Forward Reuse Distance
• Frost Prediction Using Machine Learning Methods in Fars Province
• Emergent Computations in Trained Artificial Neural Networks and Real Brains
• Inspecting and Interacting with Meaningful Music Representations using VAE
• Meaningful Answer Generation of E-Commerce Question-Answering
• iCapsNets: Towards Interpretable Capsule Networks for Text Classification
• Divide-and-Conquer Adversarial Learning for High-Resolution Image and Video Enhancement
• Recurrent Neural Networks for anomaly detection in the Post-Mortem time series of LHC superconducting magnets
• Syntactically Informed Text Compression with Recurrent Neural Networks
• Deep Risk Model: A Deep Learning Solution for Mining Latent Risk Factors to Improve Covariance Matrix Estimation
• End-to-End Video Classification with Knowledge Graphs
• HOI-aware Adaptive Network for Weakly-supervised Action Segmentation
• ECAS-ML: Edge Computing Assisted Adaptation Scheme with Machine Learning for HTTP Adaptive Streaming
• Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection
• Interpretable Crowd Flow Prediction with Spatial-Temporal Self-Attention
• The Ant Swarm Neuro-Evolution Procedure for Optimizing Recurrent Networks
• Generalized Zero-shot ICD Coding
• Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting
• Predicting small molecules solubilities on endpoint devices using deep ensemble neural networks
• Visual Question Answering on 360° Images
• Text-to-Image Generation with Attention Based Recurrent Neural Networks
• How Powerful are Interest Diffusion on Purchasing Prediction: A Case Study of Taocode
• Distributed Heuristic Multi-Agent Path Finding with Communication
• An Attention Mechanism for Answer Selection Using a Combined Global and Local View
• T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model
• Trimming and Improving Skip-thought Vectors
• Neural Response Generation with Meta-Words
• DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Range
• New Item Consumption Prediction Using Deep Learning
• LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval
• Music Artist Classification with Convolutional Recurrent Neural Networks
• Tricks from Deep Learning
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Delhi air quality prediction using LSTM deep learning models with a focus on COVID-19 lockdown
• Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series
• Voice Cloning: a Multi-Speaker Text-to-Speech Synthesis Approach based on Transfer Learning
• Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
• Neural Network for NILM Based on Operational State Change Classification
• Deep Semi-Supervised Learning with Linguistically Motivated Sequence Labeling Task Hierarchies
• Simplified Long Short-term Memory Recurrent Neural Networks: part III
• GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media
• A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
• Neural Turtle Graphics for Modeling City Road Layouts
• Trajectory-based Radical Analysis Network for Online Handwritten Chinese Character Recognition
• Text-guided Attention Model for Image Captioning
• CoTK: An Open-Source Toolkit for Fast Development and Fair Evaluation of Text Generation
• Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization
• Instance-wise Graph-based Framework for Multivariate Time Series Forecasting
• A Heterogeneous Information Network based Cross Domain Insurance Recommendation System for Cold Start Users
• Predicting Gender by First Name Using Character-level Machine Learning
• Scaling Graph-based Deep Learning models to larger networks
• Prediction-based One-shot Dynamic Parking Pricing
• Extension of Direct Feedback Alignment to Convolutional and Recurrent Neural Network for Bio-plausible Deep Learning
• Evaluating the Performance of Machine Learning Algorithms in Financial Market Forecasting: A Comprehensive Survey
• Speech Recognition with no speech or with noisy speech
• Online Signature Verification using Recurrent Neural Network and Length-normalized Path Signature
• Surprisal-Triggered Conditional Computation with Neural Networks
• Combination of Convolutional Neural Network and Gated Recurrent Unit for Energy Aware Resource Allocation
• PassAI: explainable artificial intelligence algorithm for soccer pass analysis using multimodal information resources
• Imitating Driver Behavior with Generative Adversarial Networks
• Improving RNN Transducer Modeling for End-to-End Speech Recognition
• Segmented Graph-Bert for Graph Instance Modeling
• Multimodal Gait Recognition for Neurodegenerative Diseases
• Visual Storytelling via Predicting Anchor Word Embeddings in the Stories
• Deep learning in bioinformatics: introduction, application, and perspective in big data era
• Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis
• Methods for generating and evaluating synthetic longitudinal patient data: a systematic review
• Driver-Net: Multi-Camera Fusion for Assessing Driver Take-Over Readiness in Automated Vehicles
• Session-based Sequential Skip Prediction via Recurrent Neural Networks
• Sens-BERT: Enabling Transferability and Re-calibration of Calibration Models for Low-cost Sensors under Reference Measurements Scarcity
• An Efficient Character-Level Neural Machine Translation
• Recurrent Memory Array Structures
• A Survey on Natural Language Video Localization
• Cross-lingual Word Segmentation and Morpheme Segmentation as Sequence Labelling
• Synthetic Sample Selection via Reinforcement Learning
• Teaching Machines to Converse
• Modeling and Predicting Blood Flow Characteristics through Double Stenosed Artery from CFD simulation using Deep Learning Models
• TextNAS: A Neural Architecture Search Space tailored for Text Representation
• Sequential Keystroke Behavioral Biometrics for Mobile User Identification via Multi-view Deep Learning
• Linking emotions to behaviors through deep transfer learning
• Exploring Different Dimensions of Attention for Uncertainty Detection
• Differentiable Language Model Adversarial Attacks on Categorical Sequence Classifiers
• Automated Optical Multi-layer Design via Deep Reinforcement Learning
• A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19
• Manipulation-skill Assessment from Videos with Spatial Attention Network
• UniVSE: Robust Visual Semantic Embeddings via Structured Semantic Representations
• Simplified Gating in Long Short-term Memory (LSTM) Recurrent Neural Networks
• Snore-GANs: Improving Automatic Snore Sound Classification with Synthesized Data
• Effective Multi-Stage Training Model For Edge Computing Devices In Intrusion Detection
• XAI-Guided Enhancement of Vegetation Indices for Crop Mapping
• Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full version
• Mixture of Pre-processing Experts Model for Noise Robust Deep Learning on Resource Constrained Platforms
• Neural Logic Reasoning
• Topic Sensitive Neural Headline Generation
• Sliding Sequential CVAE with Time Variant Socially-aware Rethinking for Trajectory Prediction
• Attention Forcing for Sequence-to-sequence Model Training
• Towards Collaborative Plan Acquisition through Theory of Mind Modeling in Situated Dialogue
• NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
• Attention-based Memory Selection Recurrent Network for Language Modeling
• Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies
• Reinforced Deep Markov Models With Applications in Automatic Trading
• Personalized Event Prediction for Electronic Health Records
• Learning-based Prediction and Uplink Retransmission for Wireless Virtual Reality (VR) Network
• On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers
• A Geometric Perspective on Visual Imitation Learning
• A novel hybrid methodology of measuring sentence similarity
• Autoencoder Regularized Network For Driving Style Representation Learning
• Improving Long Handwritten Text Line Recognition with Convolutional Multi-way Associative Memory
• Few-shot Generation of Personalized Neural Surrogates for Cardiac Simulation via Bayesian Meta-Learning
• Comparison of neural network architectures for feature extraction from binary black hole merger waveforms
• Fusion Recurrent Neural Network
• HireVAE: An Online and Adaptive Factor Model Based on Hierarchical and Regime-Switch VAE
• Frame-To-Frame Consistent Semantic Segmentation
• The Referential Reader: A Recurrent Entity Network for Anaphora Resolution
• Extreme time extrapolation capabilities and thermodynamic consistency of physics-inspired Neural Networks for the 3D microstructure evolution of materials via Cahn-Hilliard flow
• Uncertainty-Aware Time-to-Event Prediction using Deep Kernel Accelerated Failure Time Models
• Rethinking Skip-thought: A Neighborhood based Approach
• Learning to Structure Long-term Dependence for Sequential Recommendation
• Graph and Recurrent Neural Network-based Vehicle Trajectory Prediction For Highway Driving
• Evaluating Impact of Social Media Posts by Executives on Stock Prices
• Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
• Recurrent Neural Network-based Model for Accelerated Trajectory Analysis in AIMD Simulations
• Multi-Graph Decoding for Code-Switching ASR
• Syntax-Infused Variational Autoencoder for Text Generation
• Stock2Vec: A Hybrid Deep Learning Framework for Stock Market Prediction with Representation Learning and Temporal Convolutional Network
• Conversational Question Answering: A Survey
• Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play
• CNNs, LSTMs, and Attention Networks for Pathology Detection in Medical Data
• Encoding-based Memory Modules for Recurrent Neural Networks
• Word Embedding Algorithms as Generalized Low Rank Models and their Canonical Form
• Transfer learning from language models to image caption generators: Better models may not transfer better
• Graph Neural Distance Metric Learning with Graph-Bert
• Learning Nonlinear State Space Models with Hamiltonian Sequential Monte Carlo Sampler
• A Language-independent and Compositional Model for Personality Trait Recognition from Short Texts
• Empirical Evaluation of RNN Architectures on Sentence Classification Task
• Constrained Variational Autoencoder for improving EEG based Speech Recognition Systems
• End-to-End Radio Traffic Sequence Recognition with Deep Recurrent Neural Networks
• A Neural Network Alternative to Non-Negative Audio Models
• Memory Visualization for Gated Recurrent Neural Networks in Speech Recognition
• A Tree Architecture of LSTM Networks for Sequential Regression with Missing Data
• deepSELF: An Open Source Deep Self End-to-End Learning Framework
• 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
• Contextual Text Embeddings for Twi
• GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction
• Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques
• Multi-Task Time Series Forecasting With Shared Attention
• Deep Autotuner: a Pitch Correcting Network for Singing Performances
• Poisoned Source Code Detection in Code Models
• A Pluggable Learned Index Method via Sampling and Gap Insertion
• Mobility-Aware Seamless Handover with MPTCP in Software-Defined HetNets
• SAFCAR: Structured Attention Fusion for Compositional Action Recognition
• ADD: Augmented Disentanglement Distillation Framework for Improving Stock Trend Forecasting
• Speech-to-Singing Conversion in an Encoder-Decoder Framework
• Towards NLP with Deep Learning: Convolutional Neural Networks and Recurrent Neural Networks for Offensive Language Identification in Social Media
• On the Discrepancy between Density Estimation and Sequence Generation
• Generating Nontrivial Melodies for Music as a Service
• Sequential modeling of Sessions using Recurrent Neural Networks for Skip Prediction
• Re-balancing Variational Autoencoder Loss for Molecule Sequence Generation
• Piecewise Linear Units Improve Deep Neural Networks
• QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning
• Exploring Generalization Ability of Pretrained Language Models on Arithmetic and Logical Reasoning
• KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos
• Controlling Utterance Length in NMT-based Word Segmentation with Attention
• Tensor Networks for Multi-Modal Non-Euclidean Data
• Causal Hidden Markov Model for Time Series Disease Forecasting
• A Multifaceted Evaluation of Neural versus Phrase-Based Machine Translation for 9 Language Directions
• A Stock Selection Method Based on Earning Yield Forecast Using Sequence Prediction Models
• ConQueR: Contextualized Query Reduction using Search Logs
• Learning to Adaptively Scale Recurrent Neural Networks
• Efficient Heuristic Generation for Robot Path Planning with Recurrent Generative Model
• GMP-AR: Granularity Message Passing and Adaptive Reconciliation for Temporal Hierarchy Forecasting
• ManifoldNorm: Extending normalizations on Riemannian Manifolds
• Recurrent Value Functions
• Applying Cyclical Learning Rate to Neural Machine Translation
• Knowledge-Enriched Visual Storytelling
• Towards Interpretable Multilingual Detection of Hate Speech against Immigrants and Women in Twitter at SemEval-2019 Task 5
• Music Generation with Temporal Structure Augmentation
• Ensemble Deep Learning on Time-Series Representation of Tweets for Rumor Detection in Social Media
• A Novel Multimodal Music Genre Classifier using Hierarchical Attention and Convolutional Neural Network
• Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
• An Ensemble Dialogue System for Facts-Based Sentence Generation
• NELEC at SemEval-2019 Task 3: Think Twice Before Going Deep
• Efficient Bitrate Ladder Construction using Transfer Learning and Spatio-Temporal Features
• Deep Autotuner: A Data-Driven Approach to Natural-Sounding Pitch Correction for Singing Voice in Karaoke Performances
• Toward 3D Object Reconstruction from Stereo Images
• Comprehensive Evaluation of Deep Learning Architectures for Prediction of DNA/RNA Sequence Binding Specificities
• When Can Self-Attention Be Replaced by Feed Forward Layers?
• Improving EEG based continuous speech recognition using GAN
• A Hierarchical Deep Convolutional Neural Network and Gated Recurrent Unit Framework for Structural Damage Detection
• Listen, Look and Deliberate: Visual context-aware speech recognition using pre-trained text-video representations
• Instrument-Independent Dastgah Recognition of Iranian Classical Music Using AzarNet
• Evaluating Text-to-Image Matching using Binary Image Selection (BISON)
• A GRU-based Mixture Density Network for Data-Driven Dynamic Stochastic Programming
• UIBert: Learning Generic Multimodal Representations for UI Understanding
• Learning Trajectories for Visual-Inertial System Calibration via Model-based Heuristic Deep Reinforcement Learning
• Lightweight Temporal Self-Attention for Classifying Satellite Image Time Series
• SCNet: A Neural Network for Automated Side-Channel Attack
• Coarse-to-fine: A RNN-based hierarchical attention model for vehicle re-identification
• UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks
• SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory
• HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs
• On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra-observer Variability in 2D Echocardiography Quality Assessment
• WSRNet: Joint Spotting and Recognition of Handwritten Words
• Data-driven Hedging of Stock Index Options via Deep Learning
• Enriching Conversation Context in Retrieval-based Chatbots
• Ask Me Even More: Dynamic Memory Tensor Networks (Extended Model)
• Hierarchical Memory Decoding for Video Captioning
• An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters
• Accelerating Recommender Systems via Hardware "scale-in"
• Event Ticket Price Prediction with Deep Neural Network on Spatial-Temporal Sparse Data
• Discovering Predictable Latent Factors for Time Series Forecasting
• Empirical Autopsy of Deep Video Captioning Frameworks
• Towards Proactively Forecasting Sentence-Specific Information Popularity within Online News Documents
• PoseConvGRU: A Monocular Approach for Visual Ego-motion Estimation by Learning
• SCR-Graph: Spatial-Causal Relationships based Graph Reasoning Network for Human Action Prediction
• GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures
• Audio-replay attack detection countermeasures
• Challenges and Opportunities of Speech Recognition for Bengali Language
• Dynamic Sequential Graph Learning for Click-Through Rate Prediction
• Investigating how well contextual features are captured by bi-directional recurrent neural network models
• Survey: Transformer based Video-Language Pre-training
• An Interpretable Framework for Drug-Target Interaction with Gated Cross Attention
• Graph-Embedded Multi-Agent Learning for Smart Reconfigurable THz MIMO-NOMA Networks
• Character-Based Text Classification using Top Down Semantic Model for Sentence Representation
• Coarse-grained decomposition and fine-grained interaction for multi-hop question answering
• Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning
• Modeling Information Need of Users in Search Sessions
• High-Quality Vocoding Design with Signal Processing for Speech Synthesis and Voice Conversion
• MUSE: Multi-Scale Temporal Features Evolution for Knowledge Tracing
• Online hyperparameter optimization by real-time recurrent learning
• Memory Augmented Multi-Instance Contrastive Predictive Coding for Sequential Recommendation
• Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks
• Drug Package Recommendation via Interaction-aware Graph Induction
• 3D Human motion anticipation and classification
• I am Robot: Neuromuscular Reinforcement Learning to Actuate Human Limbs through Functional Electrical Stimulation
• Deep Time Series Models for Scarce Data
• Predictive Precompute with Recurrent Neural Networks
• An Optimized and Energy-Efficient Parallel Implementation of Non-Iteratively Trained Recurrent Neural Networks
• A Deep Neural Framework for Contextual Affect Detection
• Sequence-to-Set Semantic Tagging: End-to-End Multi-label Prediction using Neural Attention for Complex Query Reformulation and Automated Text Categorization
• H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model
• Hierarchical Hidden Markov Jump Processes for Cancer Screening Modeling
• An approach to constraining the Higgs width at the LHC and HL-LHC
• Assessing the Memory Ability of Recurrent Neural Networks
• Sensor Fusion: Gated Recurrent Fusion to Learn Driving Behavior from Temporal Multimodal Data
• DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs
• 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
• Advances in Collaborative Filtering and Ranking
• Asking Complex Questions with Multi-hop Answer-focused Reasoning
• 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
• Detecting Potential Topics In News Using BERT, CRF and Wikipedia
• PR-NN: RNN-based Detection for Coded Partial-Response Channels
• Generating a Machine-learned Equation of State for Fluid Properties
• Dereverberation using joint estimation of dry speech signal and acoustic system
• G5: A Universal GRAPH-BERT for Graph-to-Graph Transfer and Apocalypse Learning
• Understanding effect of speech perception in EEG based speech recognition systems
• Continual Learning Augmented Investment Decisions
• Improving Neuroevolution Using Island Extinction and Repopulation
• Minimum Latency Training Strategies for Streaming Sequence-to-Sequence ASR
• Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification
• An RNN-Survival Model to Decide Email Send Times
• Real-time low-resource phoneme recognition on edge devices
• Self-supervised Regularization for Text Classification
• Video Summarization via Actionness Ranking
• You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
• A framework to compare music generative models using automatic evaluation metrics extended to rhythm
• Training Image Selection using Recurrent Neural Networks: An Application in Hydrogeology
• Deep Attention-based Representation Learning for Heart Sound Classification
• Expanding the Text Classification Toolbox with Cross-Lingual Embeddings
• Channel Gain Cartography via Mixture of Experts
• Small Footprint Convolutional Recurrent Networks for Streaming Wakeword Detection
• Intention-Based Lane Changing and Lane Keeping Haptic Guidance Steering System
• Lets Play Music: Audio-driven Performance Video Generation
• Deep Multi-view Depth Estimation with Predicted Uncertainty
• Multi-Task Learning for Argumentation Mining
• Music Playlist Title Generation: A Machine-Translation Approach
• Improved RAMEN: Towards Domain Generalization for Visual Question Answering
• Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting
• PSTN: Periodic Spatial-temporal Deep Neural Network for Traffic Condition Prediction
• A Semi-Supervised Approach for Low-Resourced Text Generation
• SVP-CF: Selection via Proxy for Collaborative Filtering Data
• A Strong and Robust Baseline for Text-Image Matching
• Intelligent Link Adaptation for Grant-Free Access Cellular Networks: A Distributed Deep Reinforcement Learning Approach
• Memory and attention in deep learning
• FallDeF5: A Fall Detection Framework Using 5G-based Deep Gated Recurrent Unit Networks
• Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference
• A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems
• Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
• Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN
• Dimensioning of V2X Services in 5G Networks through Forecast-based Scaling
• Variational Sequential Labelers for Semi-Supervised Learning
• Compositional Structure Learning for Sequential Video Data
• Recurrent Estimation of Distributions
• Deep Fisher Discriminant Learning for Mobile Hand Gesture Recognition
• Sensor Transformation Attention Networks
• Curiosity as a Self-Supervised Method to Improve Exploration in De novo Drug Design
• NeuroTrainer: An Intelligent Memory Module for Deep Learning Training
• Bringing Semantic Structures to User Intent Detection in Online Medical Queries
• Towards neural reinforcement learning for large deviations in nonequilibrium systems with memory
• Self-view Grounding Given a Narrated 360° Video
• Cavs: A Vertex-centric Programming Interface for Dynamic Neural Networks
• Bert4XMR: Cross-Market Recommendation with Bidirectional Encoder Representations from Transformer
• Predicting Patient State-of-Health using Sliding Window and Recurrent Classifiers
• Infrastructure-based End-to-End Learning and Prevention of Driver Failure
• Empirical Evaluation of A New Approach to Simplifying Long Short-term Memory (LSTM)
• Channel Assignment in Uplink Wireless Communication using Machine Learning Approach
• Domain Adaptation via Teacher-Student Learning for End-to-End Speech Recognition
• Continuous Speech Recognition using EEG and Video
• Amharic-Arabic Neural Machine Translation
• Empirical Analysis of Limits for Memory Distance in Recurrent Neural Networks
• Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data
• Robust Unsupervised Multi-Object Tracking in Noisy Environments
• Two-stream Spatiotemporal Feature for Video QA Task
• Conversational Help for Task Completion and Feature Discovery in Personal Assistants
• Click-Through Rate Prediction with the User Memory Network
• CMF: Cascaded Multi-model Fusion for Referring Image Segmentation
• Detection of Consonant Errors in Disordered Speech Based on Consonant-vowel Segment Embedding
• Building Intelligent Autonomous Navigation Agents
• Clustering Vietnamese Conversations From Facebook Page To Build Training Dataset For Chatbot
• Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
• Contrastive Semantic Similarity Learning for Image Captioning Evaluation with Intrinsic Auto-encoder
• Recurrently Estimating Reflective Symmetry Planes from Partial Pointclouds
• A Topic Guided Pointer-Generator Model for Generating Natural Language Code Summaries
• Single Model for Influenza Forecasting of Multiple Countries by Multi-task Learning
• Modeling Musical Structure with Artificial Neural Networks
• PocketVAE: A Two-step Model for Groove Generation and Control
• CRNN: A Joint Neural Network for Redundancy Detection
• Recurrent Existence Determination Through Policy Optimization
• Content-Based Table Retrieval for Web Queries
• Neural Search: Learning Query and Product Representations in Fashion E-commerce
• Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking
• Learning Longer-term Dependencies via Grouped Distributor Unit
• Lyapunov-based uncertainty-aware safe reinforcement learning
• Towards the Improvement of Automated Scientific Document Categorization by Deep Learning
• RECOWNs: Probabilistic Circuits for Trustworthy Time Series Forecasting
• A Temporal Knowledge Graph Completion Method Based on Balanced Timestamp Distribution
• Target-Guided Open-Domain Conversation
• SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
• Improving Minimal Gated Unit for Sequential Data
• #StayHome or #Marathon? Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs
• Character-Aware Attention-Based End-to-End Speech Recognition
• Predicting Annotation Difficulty to Improve Task Routing and Model Performance for Biomedical Information Extraction
• Contrastive Representation Learning for Exemplar-Guided Paraphrase Generation
• Edge-featured Graph Neural Architecture Search
• Opinion Prediction with User Fingerprinting
• A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification
• Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization
• Progressively Guide to Attend: An Iterative Alignment Framework for Temporal Sentence Grounding
• Topical Behavior Prediction from Massive Logs
• Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• Equivariant Neural Network for Factor Graphs
• Efficient Modelling Across Time of Human Actions and Interactions
• Improving Multi-Party Dialogue Discourse Parsing via Domain Integration
• Using Clinical Drug Representations for Improving Mortality and Length of Stay Predictions
• Using Context Information to Enhance Simple Question Answering
• Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting
• DeepFoldit -- A Deep Reinforcement Learning Neural Network Folding Proteins
• CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing
• Template Controllable keywords-to-text Generation
• ConFuse: Convolutional Transform Learning Fusion Framework For Multi-Channel Data Analysis
• Network of Recurrent Neural Networks
• Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks
• Automating App Review Response Generation
• Improving Clinical Outcome Predictions Using Convolution over Medical Entities with Multimodal Learning
• TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation
• Reciprocal Supervised Learning Improves Neural Machine Translation
• CASE: Context-Aware Semantic Expansion
• Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach
• From syntactic structure to semantic relationship: hypernym extraction from definitions by recurrent neural networks using the part of speech information
• Research on All-content Text Recognition Method for Financial Ticket Image
• R${}^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching
• Improve Diverse Text Generation by Self Labeling Conditional Variational Auto Encoder
• Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers
• Hybrid Interest Modeling for Long-tailed Users
• TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
• Modeling Irregular Astronomical Time Series with Neural Stochastic Delay Differential Equations
• Pricing spread option with liquidity adjustments
• Research on Fast Text Recognition Method for Financial Ticket Image
• Network Horizon Dynamics I: Qualitative Aspects
• ArrowGAN : Learning to Generate Videos by Learning Arrow of Time
• HinFlair: pre-trained contextual string embeddings for pos tagging and text classification in the Hindi language
• Edge-Labeling based Directed Gated Graph Network for Few-shot Learning
• Learning Preferences and Demands in Visual Recommendation
• The Role of the Input in Natural Language Video Description
• Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation
• Introducing the Hidden Neural Markov Chain framework
• Enhancing Reinforcement Learning Through Guided Search
• A Concept Knowledge-Driven Keywords Retrieval Framework for Sponsored Search
• Understanding Feature Selection and Feature Memorization in Recurrent Neural Networks
• LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment
• Point Cloud Processing via Recurrent Set Encoding
• Weather Analogs with a Machine Learning Similarity Metric for Renewable Resource Forecasting
• Learning a Word-Level Language Model with Sentence-Level Noise Contrastive Estimation for Contextual Sentence Probability Estimation
• Dual Attention Network for Product Compatibility and Function Satisfiability Analysis
• Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems
• Sent2Matrix: Folding Character Sequences in Serpentine Manifolds for Two-Dimensional Sentence
• Domain-Constrained Advertising Keyword Generation
• Two-stage training algorithm for AI robot soccer
• An Empirical Framework for Domain Generalization in Clinical Settings
• Deep Chaos Synchronization
• OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas
• A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect
• Evaluating Bregman Divergences for Probability Learning from Crowd
• Siamese Neural Networks for Class Activity Detection
• Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots
• Visualizing Semantic Structures of Sequential Data by Learning Temporal Dependencies
• Predicting Different Acoustic Features from EEG and towards direct synthesis of Audio Waveform from EEG
• Pedestrian Tracking with Gated Recurrent Units and Attention Mechanisms
• Joint Forecasting and Interpolation of Graph Signals Using Deep Learning
• Neuroevolutionary Transfer Learning of Deep Recurrent Neural Networks through Network-Aware Adaptation
• Iterative Edit-Based Unsupervised Sentence Simplification
• Efficient text generation of user-defined topic using generative adversarial networks
• 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
• MEETING BOT: Reinforcement Learning for Dialogue Based Meeting Scheduling
• Deep Learning based, end-to-end metaphor detection in Greek language with Recurrent and Convolutional Neural Networks
• Graph Wasserstein Correlation Analysis for Movie Retrieval
• Label-Conditioned Next-Frame Video Generation with Neural Flows
• Comprehensive forecasting based analysis using stacked stateless and stateful Gated Recurrent Unit models
• Forecasting with Multiple Seasonality
• Efficient Global String Kernel with Random Features: Beyond Counting Substructures
• A Probabilistic Framework for Learning Domain Specific Hierarchical Word Embeddings
• Read Beyond the Lines: Understanding the Implied Textual Meaning via a Skim and Intensive Reading Model
• 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
• Grounding Complex Navigational Instructions Using Scene Graphs
• Neural Auto-Curricula
• Incremental Learning from Scratch for Task-Oriented Dialogue Systems
• Graph Convolutional Memory using Topological Priors
• Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
• An Experimental Study of Weight Initialization and Weight Inheritance Effects on Neuroevolution
• A Coarse to Fine Question Answering System based on Reinforcement Learning
• Text Classification with Lexicon from PreAttention Mechanism
• Conversational Fashion Image Retrieval via Multiturn Natural Language Feedback
• CITIES: Contextual Inference of Tail-Item Embeddings for Sequential Recommendation
• Temporally Folded Convolutional Neural Networks for Sequence Forecasting
• 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
• Conversational Response Re-ranking Based on Event Causality and Role Factored Tensor Event Embedding
• Latent Multi-Criteria Ratings for Recommendations
• DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching
• Distributed Learning and its Application for Time-Series Prediction
• SGE net: Video object detection with squeezed GRU and information entropy map
• Neural Image Captioning
• Predict your Click-out: Modeling User-Item Interactions and Session Actions in an Ensemble Learning Fashion
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection
• Unsupervised Abstractive Opinion Summarization by Generating Sentences with Tree-Structured Topic Guidance
• From Cities to Series: Complex Networks and Deep Learning for Improved Spatial and Temporal Analytics*