Improving neural networks by preventing co-adaptation of feature detectors

Abstract

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case. This prevents complex co-adaptations in which a feature detector is only helpful in the context of several other specific feature detectors. Instead, each neuron learns to detect a feature that is generally helpful for producing the correct answer given the combinatorially large variety of internal contexts in which it must operate. Random "dropout" gives big improvements on many benchmark tasks and sets new records for speech and object recognition.

References in corpus (1)

• Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition

Cited by in corpus (1079)

• Adam: A Method for Stochastic Optimization
• Deep Learning in Neural Networks: An Overview
• Distilling the Knowledge in a Neural Network
• Conditional Generative Adversarial Nets
• Deep Residual Learning for Image Recognition
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• How transferable are features in deep neural networks?
• Character-level Convolutional Networks for Text Classification
• Learning Transferable Features with Deep Adaptation Networks
• Improved Regularization of Convolutional Neural Networks with Cutout
• Striving for Simplicity: The All Convolutional Net
• Covid-19: Automatic detection from X-Ray images utilizing Transfer Learning with Convolutional Neural Networks
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
• Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• Attention-Based Models for Speech Recognition
• Deep Facial Expression Recognition: A Survey
• A continual learning survey: Defying forgetting in classification tasks
• Learning Face Representation from Scratch
• Understanding Neural Networks Through Deep Visualization
• Do Deep Nets Really Need to be Deep?
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
• Weight Uncertainty in Neural Networks
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Convolutional Neural Networks for Sentence Classification
• Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway
• fPINNs: Fractional Physics-Informed Neural Networks
• Deep Learning with Limited Numerical Precision
• Deeply-Supervised Nets
• Character-Aware Neural Language Models
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• An Introduction to Convolutional Neural Networks
• DeepID3: Face Recognition with Very Deep Neural Networks
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• A Survey on Distributed Machine Learning
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
• A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
• Opening the Black Box of Deep Neural Networks via Information
• Unsupervised Deep Feature Extraction for Remote Sensing Image Classification
• Deep learning for molecular design - a review of the state of the art
• Predicting Parameters in Deep Learning
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• FractalNet: Ultra-Deep Neural Networks without Residuals
• Improving Computer-aided Detection using Convolutional Neural Networks and Random View Aggregation
• WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis
• Residual Networks Behave Like Ensembles of Relatively Shallow Networks
• Deep Bayesian Active Learning with Image Data
• Training Deep Neural Networks on Noisy Labels with Bootstrapping
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
• Speeding up Convolutional Neural Networks with Low Rank Expansions
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Deep image mining for diabetic retinopathy screening
• The Goldilocks Principle: Reading Children's Books with Explicit Memory Representations
• On Using Monolingual Corpora in Neural Machine Translation
• Land Use Classification in Remote Sensing Images by Convolutional Neural Networks
• Data Augmentation using Random Image Cropping and Patching for Deep CNNs
• A Convolutional Neural Network for Modelling Sentences
• A Review on Deep Learning in UAV Remote Sensing
• Hyper-Parameter Optimization: A Review of Algorithms and Applications
• Medical Image Retrieval using Deep Convolutional Neural Network
• Optimizing Neural Networks with Kronecker-factored Approximate Curvature
• Variational Dropout and the Local Reparameterization Trick
• Optic Disc and Cup Segmentation Methods for Glaucoma Detection with Modification of U-Net Convolutional Neural Network
• Scalable Bayesian Optimization Using Deep Neural Networks
• Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects
• Large-Margin Softmax Loss for Convolutional Neural Networks
• Visualizing and Understanding Convolutional Networks
• Gabor Convolutional Networks
• Text Understanding from Scratch
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results
• Residual Networks of Residual Networks: Multilevel Residual Networks
• Deep Learning and its Application to LHC Physics
• Advancements in Image Classification using Convolutional Neural Network
• Large-Scale Optical Neural Networks based on Photoelectric Multiplication
• SMASH: One-Shot Model Architecture Search through HyperNetworks
• Generative Moment Matching Networks
• Some Improvements on Deep Convolutional Neural Network Based Image Classification
• Learning with Pseudo-Ensembles
• Learning Activation Functions to Improve Deep Neural Networks
• Distributional Smoothing with Virtual Adversarial Training
• Bayesian Compression for Deep Learning
• Data Augmentation by Pairing Samples for Images Classification
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Reducing Complexity of HEVC: A Deep Learning Approach
• Variational Dropout Sparsifies Deep Neural Networks
• Towards Dropout Training for Convolutional Neural Networks
• Recent Advances in Convolutional Neural Networks
• Compute Trends Across Three Eras of Machine Learning
• Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups
• Deep Generative Stochastic Networks Trainable by Backprop
• R-Drop: Regularized Dropout for Neural Networks
• Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling
• Mixed Neural Network Approach for Temporal Sleep Stage Classification
• Diagnosis of Alzheimer's Disease via Multi-modality 3D Convolutional Neural Network
• Training deep neural networks with low precision multiplications
• Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
• Learning Discrete Representations via Information Maximizing Self-Augmented Training
• Maximum Entropy Deep Inverse Reinforcement Learning
• Reducing Transformer Depth on Demand with Structured Dropout
• Deep Convolutional Ranking for Multilabel Image Annotation
• Dropout Training as Adaptive Regularization
• Learning with a Strong Adversary
• Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding
• How to Construct Deep Recurrent Neural Networks
• Neuromorphic Deep Learning Machines
• Continuous online sequence learning with an unsupervised neural network model
• Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
• Multimodal Residual Learning for Visual QA
• ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks
• Making brain-machine interfaces robust to future neural variability
• DeepSign: Deep Learning for Automatic Malware Signature Generation and Classification
• Loss Functions for Neural Networks for Image Processing
• Stacked What-Where Auto-encoders
• Multi-Modal Self-Supervised Learning for Recommendation
• Star-galaxy Classification Using Deep Convolutional Neural Networks
• Deep Learning of Part-based Representation of Data Using Sparse Autoencoders with Nonnegativity Constraints
• Deep learning of multi-element abundances from high-resolution spectroscopic data
• Identity Mappings in Deep Residual Networks
• Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
• Spatially-sparse convolutional neural networks
• Learning Human Pose Estimation Features with Convolutional Networks
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Pylearn2: a machine learning research library
• Pooling Methods in Deep Neural Networks, a Review
• Regularization for Deep Learning: A Taxonomy
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• Deep convolutional networks for pancreas segmentation in CT imaging
• Winner-Take-All Autoencoders
• Text Matching as Image Recognition
• A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
• Simultaneous calibration of spectro-photometric distances and the Gaia DR2 parallax zero-point offset with deep learning
• Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
• SSDH: Semi-supervised Deep Hashing for Large Scale Image Retrieval
• A Comprehensive guide to Bayesian Convolutional Neural Network with Variational Inference
• Less-forgetting Learning in Deep Neural Networks
• Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks
• Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge and Skeleton
• Audiovisual SlowFast Networks for Video Recognition
• DeepMood: Modeling Mobile Phone Typing Dynamics for Mood Detection
• The Strong Gravitational Lens Finding Challenge
• Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks
• Multi-task Neural Networks for QSAR Predictions
• Non-local Neural Networks
• Mixing Dirichlet Topic Models and Word Embeddings to Make lda2vec
• Writer-independent Feature Learning for Offline Signature Verification using Deep Convolutional Neural Networks
• An Entropy-based Pruning Method for CNN Compression
• k-Sparse Autoencoders
• SlowFast Networks for Video Recognition
• No bad local minima: Data independent training error guarantees for multilayer neural networks
• Conditional Computation in Neural Networks for faster models
• Network Plasticity as Bayesian Inference
• Machine-learning-assisted correction of correlated qubit errors in a topological code
• Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
• DART: Dropouts meet Multiple Additive Regression Trees
• Revisiting Self-Training for Neural Sequence Generation
• On the Performance of ConvNet Features for Place Recognition
• Finding strong lenses in CFHTLS using convolutional neural networks
• Knowledge Matters: Importance of Prior Information for Optimization
• Beating the Perils of Non-Convexity: Guaranteed Training of Neural Networks using Tensor Methods
• Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
• Shallow and Deep Convolutional Networks for Saliency Prediction
• DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation
• Deep learning for source camera identification on mobile devices
• Memory Bounded Deep Convolutional Networks
• Deep Networks with Internal Selective Attention through Feedback Connections
• Pix2seq: A Language Modeling Framework for Object Detection
• Lagged correlation-based deep learning for directional trend change prediction in financial time series
• Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
• Genetic Algorithms for Evolving Deep Neural Networks
• Do CIFAR-10 Classifiers Generalize to CIFAR-10?
• On the number of response regions of deep feed forward networks with piece-wise linear activations
• A Comprehensive Analysis of the Role of Artificial Intelligence and Machine Learning in Modern Digital Forensics and Incident Response
• Freeze-Thaw Bayesian Optimization
• Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
• Search for charged Higgs bosons decaying into a top quark and a bottom quark at $\sqrt{s}$=13 TeV with the ATLAS detector
• Deep Learning of Representations: Looking Forward
• Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
• Two-Stream 3D Convolutional Neural Network for Skeleton-Based Action Recognition
• Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path
• Deep learning generalizes because the parameter-function map is biased towards simple functions
• B-CNN: Branch Convolutional Neural Network for Hierarchical Classification
• Dropout Inference in Bayesian Neural Networks with Alpha-divergences
• APAC: Augmented PAttern Classification with Neural Networks
• Machine Learning techniques for state recognition and auto-tuning in quantum dots
• Scale-Invariant Convolutional Neural Networks
• ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
• Finding high-redshift strong lenses in DES using convolutional neural networks
• Enhanced Higgs to ${\tau }^{+}{\tau }^{-}$ Searches with Deep Learning
• Recover Canonical-View Faces in the Wild with Deep Neural Networks
• A Rotation-Invariant Framework for Deep Point Cloud Analysis
• Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification
• Approaching the Computational Color Constancy as a Classification Problem through Deep Learning
• End-to-End Text Recognition with Hybrid HMM Maxout Models
• Learning 3D Mineral Prospectivity from 3D Geological Models Using Convolutional Neural Networks: Application to a Structure-controlled Hydrothermal Gold Deposit
• Recurrent Dropout without Memory Loss
• RNADE: The real-valued neural autoregressive density-estimator
• Dropout as data augmentation
• Deep Learning for Medical Image Segmentation
• Learning Fine-grained Image Similarity with Deep Ranking
• Input Warping for Bayesian Optimization of Non-stationary Functions
• Domain Adaptive Neural Networks for Object Recognition
• Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection
• Toxicity Prediction using Deep Learning
• The Power of Sparsity in Convolutional Neural Networks
• Deep Structured Output Learning for Unconstrained Text Recognition
• Multi-Target Regression via Random Linear Target Combinations
• Neural network-based on-chip spectroscopy using a scalable plasmonic encoder
• On the Origin of Deep Learning
• Sparse arrays of signatures for online character recognition
• Physics-Driven Regularization of Deep Neural Networks for Enhanced Engineering Design and Analysis
• Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges
• Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging
• Predicting Daily Activities From Egocentric Images Using Deep Learning
• Batch-normalized Maxout Network in Network
• Object Detection with Deep Learning: A Review
• Exploiting deep residual networks for human action recognition from skeletal data
• Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms
• Fisher Vectors Derived from Hybrid Gaussian-Laplacian Mixture Models for Image Annotation
• QuipuNet: convolutional neural network for single-molecule nanopore sensing
• Exploring Randomly Wired Neural Networks for Image Recognition
• Discovering Parametric Activation Functions
• A Deep Learning-based Reconstruction of Cosmic Ray-induced Air Showers
• Combining Neural Networks and Log-linear Models to Improve Relation Extraction
• Detection of Anomalies in Large Scale Accounting Data using Deep Autoencoder Networks
• Avoiding pathologies in very deep networks
• Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods
• Probabilistic Reasoning via Deep Learning: Neural Association Models
• Deep Learning Classification in Asteroseismology
• Estimating or Propagating Gradients Through Stochastic Neurons
• Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic
• Solving inverse-PDE problems with physics-aware neural networks
• Recurrent Neural Networks for Time Series Forecasting
• FreezeOut: Accelerate Training by Progressively Freezing Layers
• Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control
• Learning Sparse Networks Using Targeted Dropout
• Dependency-based Convolutional Neural Networks for Sentence Embedding
• Convolutional Clustering for Unsupervised Learning
• LFADS - Latent Factor Analysis via Dynamical Systems
• Missing Data Imputation for Supervised Learning
• A Fast Incremental Gaussian Mixture Model
• GPU Asynchronous Stochastic Gradient Descent to Speed Up Neural Network Training
• Analyzing noise in autoencoders and deep networks
• Revisiting Self-Supervised Visual Representation Learning
• Center-based 3D Object Detection and Tracking
• Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
• SPCANet: Stellar Parameters and Chemical Abundances Network for LAMOST-II Medium Resolution Survey
• Neural Sampling Machine with Stochastic Synapse allows Brain-like Learning and Inference
• Deep Learning with Low Precision by Half-wave Gaussian Quantization
• Robust Convolutional Neural Networks under Adversarial Noise
• CL4CTR: A Contrastive Learning Framework for CTR Prediction
• Deep Feature Learning for EEG Recordings
• A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data
• Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
• Deconstructing the Ladder Network Architecture
• DropMessage: Unifying Random Dropping for Graph Neural Networks
• Deep Learning of Nonnegativity-Constrained Autoencoders for Enhanced Understanding of Data
• Variational Auto-encoded Deep Gaussian Processes
• An empirical analysis of dropout in piecewise linear networks
• A Probabilistic Theory of Deep Learning
• Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting
• Tackling Over-Smoothing for General Graph Convolutional Networks
• Spatial Transformer Networks
• Uncertainty Estimations by Softplus normalization in Bayesian Convolutional Neural Networks with Variational Inference
• Neural Machine Translation with Reconstruction
• Multilingual Extractive Reading Comprehension by Runtime Machine Translation
• Analysis and Optimization of Convolutional Neural Network Architectures
• $\mathcal{G}$-softmax: Improving Intra-class Compactness and Inter-class Separability of Features
• Dropout as a Bayesian Approximation: Appendix
• Multimodal Convolutional Neural Networks for Matching Image and Sentence
• Structured Probabilistic Pruning for Convolutional Neural Network Acceleration
• RDP-Net: Region Detail Preserving Network for Change Detection
• Multiscale Vision Transformers
• Listening for Sirens: Locating and Classifying Acoustic Alarms in City Scenes
• Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures
• Conversational Contextual Cues: The Case of Personalization and History for Response Ranking
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• Effective and Efficient Dropout for Deep Convolutional Neural Networks
• Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces
• Quasi Anomalous Knowledge: Searching for new physics with embedded knowledge
• A Taxonomy and Library for Visualizing Learned Features in Convolutional Neural Networks
• Dreaming of atmospheres
• Multi-Sample Dropout for Accelerated Training and Better Generalization
• A superpixel-driven deep learning approach for the analysis of dermatological wounds
• Low-Rank Approximations for Conditional Feedforward Computation in Deep Neural Networks
• Pruning and Quantization for Deep Neural Network Acceleration: A Survey
• A Survey on Deep Learning Methods for Robot Vision
• Big Neural Networks Waste Capacity
• Love Thy Neighbors: Image Annotation by Exploiting Image Metadata
• Dropout-GAN: Learning from a Dynamic Ensemble of Discriminators
• On-Device Machine Learning: An Algorithms and Learning Theory Perspective
• Unit Tests for Stochastic Optimization
• An exploration of parameter redundancy in deep networks with circulant projections
• Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect
• Visual Causal Feature Learning
• Survey of Dropout Methods for Deep Neural Networks
• ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer
• DeLighT: Deep and Light-weight Transformer
• Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network
• Network Representation Learning: A Survey
• Using convolutional neural networks to predict galaxy metallicity from three-color images
• Improving Classifier Training Efficiency for Automatic Cyberbullying Detection with Feature Density
• Deep Temporal Appearance-Geometry Network for Facial Expression Recognition
• Regularization and Optimization strategies in Deep Convolutional Neural Network
• Are we done with object recognition? The iCub robot's perspective
• On Fast Dropout and its Applicability to Recurrent Networks
• Learning Ordered Representations with Nested Dropout
• Dropout-based Active Learning for Regression
• An Empirical Study on Writer Identification & Verification from Intra-variable Individual Handwriting
• Progressive Pose Attention Transfer for Person Image Generation
• Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• A Selective Overview of Deep Learning
• EmoNets: Multimodal deep learning approaches for emotion recognition in video
• How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets
• What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory
• When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition
• Sketch-a-Net that Beats Humans
• Bayesian Neural Networks for Genetic Association Studies of Complex Disease
• Techniques for Learning Binary Stochastic Feedforward Neural Networks
• Noisy Differentiable Architecture Search
• Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings
• Pragmatic inference and visual abstraction enable contextual flexibility during visual communication
• Zero-bias autoencoders and the benefits of co-adapting features
• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
• Efficient Gradient-Based Inference through Transformations between Bayes Nets and Neural Nets
• Classifying Exoplanet Candidates with Convolutional Neural Networks: Application to the Next Generation Transit Survey
• PatchNet: Hierarchical Deep Learning-Based Stable Patch Identification for the Linux Kernel
• Molecule Identification with Rotational Spectroscopy and Probabilistic Deep Learning
• Word Embedding Perturbation for Sentence Classification
• Learning to Discover Efficient Mathematical Identities
• Jet Constituents for Deep Neural Network Based Top Quark Tagging
• TensorSCONE: A Secure TensorFlow Framework using Intel SGX
• Recognizing Semantic Features in Faces using Deep Learning
• A Bayesian encourages dropout
• A Novel Physics-Regularized Interpretable Machine Learning Model for Grain Growth
• DecomposeMe: Simplifying ConvNets for End-to-End Learning
• H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis
• The NN-Stacking: Feature weighted linear stacking through neural networks
• Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation
• Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
• A Multi-task Ensemble Framework for Emotion, Sentiment and Intensity Prediction
• Training Neural Networks with Stochastic Hessian-Free Optimization
• Object Detection Networks on Convolutional Feature Maps
• Improved Training of Physics-Informed Neural Networks with Model Ensembles
• Automatic Instrument Recognition in Polyphonic Music Using Convolutional Neural Networks
• Automatic recognition of element classes and boundaries in the birdsong with variable sequences
• A Tutorial on Deep Latent Variable Models of Natural Language
• TAda! Temporally-Adaptive Convolutions for Video Understanding
• Discriminative Recurrent Sparse Auto-Encoders
• Regularization and nonlinearities for neural language models: when are they needed?
• Hough-CNN: Deep Learning for Segmentation of Deep Brain Regions in MRI and Ultrasound
• On Vectorization of Deep Convolutional Neural Networks for Vision Tasks
• SpeakerNet: 1D Depth-wise Separable Convolutional Network for Text-Independent Speaker Recognition and Verification
• Online Linear Optimization via Smoothing
• Hypothesis Testing and Machine Learning: Interpreting Variable Effects in Deep Artificial Neural Networks using Cohen's f2
• A Deep Learning Approach to Unsupervised Ensemble Learning
• Deep Models for Engagement Assessment With Scarce Label Information
• Online Semi-Supervised Learning with Deep Hybrid Boltzmann Machines and Denoising Autoencoders
• Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks
• Towards Understanding Label Smoothing
• Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification
• Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
• KLIFF: A framework to develop physics-based and machine learning interatomic potentials
• Highway Long Short-Term Memory RNNs for Distant Speech Recognition
• rnn : Recurrent Library for Torch
• CASTLE: Regularization via Auxiliary Causal Graph Discovery
• Efficient Object Localization Using Convolutional Networks
• The Implicit and Explicit Regularization Effects of Dropout
• A Survey: Time Travel in Deep Learning Space: An Introduction to Deep Learning Models and How Deep Learning Models Evolved from the Initial Ideas
• Zero-Shot Learning for Semantic Utterance Classification
• Simple vs complex temporal recurrences for video saliency prediction
• IoT Data Analytics Using Deep Learning
• To Drop or Not to Drop: Robustness, Consistency and Differential Privacy Properties of Dropout
• Low-Resource Text Classification using Domain-Adversarial Learning
• Online and Offline Reinforcement Learning by Planning with a Learned Model
• Is Joint Training Better for Deep Auto-Encoders?
• Exponentially Increasing the Capacity-to-Computation Ratio for Conditional Computation in Deep Learning
• Training Recurrent Neural Networks by Diffusion
• Deep Learning for Identifying Iran's Cultural Heritage Buildings in Need of Conservation Using Image Classification and Grad-CAM
• Memory-enhanced Decoder for Neural Machine Translation
• Improved Residual Networks for Image and Video Recognition
• Smooth Neighbors on Teacher Graphs for Semi-supervised Learning
• Como funciona o Deep Learning
• DropNeuron: Simplifying the Structure of Deep Neural Networks
• Understanding Deep Architectures using a Recursive Convolutional Network
• Data Recombination for Neural Semantic Parsing
• Solving Optimization Problems through Fully Convolutional Networks: an Application to the Travelling Salesman Problem
• ProbAct: A Probabilistic Activation Function for Deep Neural Networks
• ProGraML: Graph-based Deep Learning for Program Optimization and Analysis
• Interactive Attention for Neural Machine Translation
• On the Challenges of Physical Implementations of RBMs
• Dalek -- a deep-learning emulator for TARDIS
• Answer Sequence Learning with Neural Networks for Answer Selection in Community Question Answering
• Multilingual Language Processing From Bytes
• Predicting Auction Price of Vehicle License Plate with Deep Recurrent Neural Network
• Rethinking Feature Distribution for Loss Functions in Image Classification
• Joint Training of Deep Boltzmann Machines
• Efficient Gender Classification Using a Deep LDA-Pruned Net
• Learning with hidden variables
• Temporal Pyramid Network for Action Recognition
• Deep Regression for Face Alignment
• Learning Uncertain Convolutional Features for Accurate Saliency Detection
• Project Hephaistos - II. Dyson sphere candidates from Gaia DR3, 2MASS, and WISE
• A Unified Gradient Regularization Family for Adversarial Examples
• Modeling Source Syntax for Neural Machine Translation
• On the Generalization Error Bounds of Neural Networks under Diversity-Inducing Mutual Angular Regularization
• Optimized Three Deep Learning Models Based-PSO Hyperparameters for Beijing PM2.5 Prediction
• QVHighlights: Detecting Moments and Highlights in Videos via Natural Language Queries
• Task Augmentation by Rotating for Meta-Learning
• Environmental Noise Embeddings for Robust Speech Recognition
• Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size
• Deriving Neural Architectures from Sequence and Graph Kernels
• Network of Experts for Large-Scale Image Categorization
• Hierarchical learning for DNN-based acoustic scene classification
• High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps
• Catastrophic forgetting: still a problem for DNNs
• Galaxy morphology prediction using capsule networks
• Randomness In Neural Network Training: Characterizing The Impact of Tooling
• A deep learning approach for lower back-pain risk prediction during manual lifting
• Least Squares Revisited: Scalable Approaches for Multi-class Prediction
• Transition Propagation Graph Neural Networks for Temporal Networks
• Altitude Training: Strong Bounds for Single-Layer Dropout
• Sequence Model Design for Code Completion in the Modern IDE
• Learnable Bernoulli Dropout for Bayesian Deep Learning
• Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation
• Unsupervised Deep Haar Scattering on Graphs
• Towards Optimally Weighted Physics-Informed Neural Networks in Ocean Modelling
• Dropout as a Low-Rank Regularizer for Matrix Factorization
• Max-Pooling Dropout for Regularization of Convolutional Neural Networks
• Churn analysis using deep convolutional neural networks and autoencoders
• Learning unbiased features
• Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification
• Particle Identification In Camera Image Sensors Using Computer Vision
• Predicting Audience's Laughter Using Convolutional Neural Network
• An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking
• Stochastic Shared Embeddings: Data-driven Regularization of Embedding Layers
• An Attentive Sequence Model for Adverse Drug Event Extraction from Biomedical Text
• Multichannel Variable-Size Convolution for Sentence Classification
• A survey of Object Classification and Detection based on 2D/3D data
• Selective Unsupervised Feature Learning with Convolutional Neural Network (S-CNN)
• Neural Decision Trees
• Hexagonal Image Processing in the Context of Machine Learning: Conception of a Biologically Inspired Hexagonal Deep Learning Framework
• Semi-Supervised Sequence Modeling with Cross-View Training
• Flip-Rotate-Pooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification
• Multi-path Convolutional Neural Networks for Complex Image Classification
• Safe end-to-end imitation learning for model predictive control
• Towards Robust Neural Machine Translation
• Comparing Rule-Based and Deep Learning Models for Patient Phenotyping
• Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection
• LULC classification methodology based on simple Convolutional Neural Network to map complex urban forms at finer scale: Evidence from Mumbai
• Extensions of stability selection using subsamples of observations and covariates
• Application of Deep Neural Networks to assess corporate Credit Rating
• On the Inductive Bias of Dropout
• SimNets: A Generalization of Convolutional Networks
• Twitter Bot Detection Using Bidirectional Long Short-term Memory Neural Networks and Word Embeddings
• Object Recognition Using Deep Neural Networks: A Survey
• Bayesian Deep Learning for Exoplanet Atmospheric Retrieval
• LCA: Loss Change Allocation for Neural Network Training
• Tensor Regression Networks with various Low-Rank Tensor Approximations
• Using Web Co-occurrence Statistics for Improving Image Categorization
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• Conversational Analysis using Utterance-level Attention-based Bidirectional Recurrent Neural Networks
• Universal Image Manipulation Detection using Deep Siamese Convolutional Neural Network
• End-to-end Convolutional Network for Saliency Prediction
• Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation
• Half-CNN: A General Framework for Whole-Image Regression
• Machine learning surrogates for efficient hydrologic modeling: Insights from stochastic simulations of managed aquifer recharge
• Estimating Cosmological Parameters from the Dark Matter Distribution
• Image Based Identification of Ghanaian Timbers Using the XyloTron: Opportunities, Risks and Challenges
• A Bayesian Deep Learning Approach to Near-Term Climate Prediction
• A PCA-Based Convolutional Network
• Machine learning and AI research for Patient Benefit: 20 Critical Questions on Transparency, Replicability, Ethics and Effectiveness
• Quantum State Tomography with Conditional Generative Adversarial Networks
• Time-aware Large Kernel Convolutions
• How degenerate is the parametrization of neural networks with the ReLU activation function?
• Adversarial TableQA: Attention Supervision for Question Answering on Tables
• GaborNet: Gabor filters with learnable parameters in deep convolutional neural networks
• Hyperparameter Optimization and Boosting for Classifying Facial Expressions: How good can a "Null" Model be?
• Knowledge Projection for Deep Neural Networks
• Treelogy: A Novel Tree Classifier Utilizing Deep and Hand-crafted Representations
• Referenceless Quality Estimation for Natural Language Generation
• MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond
• ThUnderVolt: Enabling Aggressive Voltage Underscaling and Timing Error Resilience for Energy Efficient Deep Neural Network Accelerators
• Funnel Activation for Visual Recognition
• Exploring Deep and Recurrent Architectures for Optimal Control
• Telugu OCR Framework using Deep Learning
• Enhancing Rumor Detection in Social Media Using Dynamic Propagation Structures
• Exploring the Landscape of Ubiquitous In-home Health Monitoring: A Comprehensive Survey
• Understanding Locally Competitive Networks
• The Winning Solution to the IEEE CIG 2017 Game Data Mining Competition
• Dropout Training for Support Vector Machines
• Improving the Robustness of Speech Translation
• On Convergence and Generalization of Dropout Training
• Combining the Best of Graphical Models and ConvNets for Semantic Segmentation
• Adapting Resilient Propagation for Deep Learning
• Variational Inference with Hamiltonian Monte Carlo
• A graph-based probabilistic geometric deep learning framework with online enforcement of physical constraints to predict the criticality of defects in porous materials
• Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding
• Multi-Label Classification with Label Graph Superimposing
• Machine Vision for Natural Gas Methane Emissions Detection Using an Infrared Camera
• Teaching Deep Convolutional Neural Networks to Play Go
• Artificial Intelligence Model for Tumoral Clinical Decision Support Systems
• Dropout with Expectation-linear Regularization
• Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis
• LocalDrop: A Hybrid Regularization for Deep Neural Networks
• Transparency and Explanation in Deep Reinforcement Learning Neural Networks
• On Training Implicit Models
• Task-Oriented Learning of Word Embeddings for Semantic Relation Classification
• Prototype-based Neural Network Layers: Incorporating Vector Quantization
• Probing Convolutional Neural Networks for Event Reconstruction in γ-Ray Astronomy with Cherenkov Telescopes
• Why Regularized Auto-Encoders learn Sparse Representation?
• Parameterized Hypercomplex Graph Neural Networks for Graph Classification
• "When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware Attention Framework for Relationship Extraction
• Indexing of CNN Features for Large Scale Image Search
• Reliable training and estimation of variance networks
• Adaptive Sampling for Stochastic Risk-Averse Learning
• CNN Based Hashing for Image Retrieval
• Manifold Regularized Deep Neural Networks using Adversarial Examples
• Learning to Remember Translation History with a Continuous Cache
• Generic Object Detection With Dense Neural Patterns and Regionlets
• Deep Learning Optimized Sparse Antenna Activation for Reconfigurable Intelligent Surface Assisted Communication
• Pushing the bounds of dropout
• Deep Reinforcement Learning for Chinese Zero pronoun Resolution
• Deep Neural Networks for Detecting Statistical Model Misspecifications. The Case of Measurement Invariance
• Cross-domain Semantic Parsing via Paraphrasing
• DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference
• Accenture at CheckThat! 2020: If you say so: Post-hoc fact-checking of claims using transformer-based models
• Dropout: Explicit Forms and Capacity Control
• Fully DNN-based Multi-label regression for audio tagging
• Optimization of Quantum-dot Qubit Fabrication via Machine Learning
• Improved Dropout for Shallow and Deep Learning
• Compacting Neural Network Classifiers via Dropout Training
• Attended End-to-end Architecture for Age Estimation from Facial Expression Videos
• Implementation of Deep Convolutional Neural Network in Multi-class Categorical Image Classification
• Deep learning Local Reduced Density Matrices for Many-body Hamiltonian Estimation
• Sequential Deep Learning for Credit Risk Monitoring with Tabular Financial Data
• Discriminative Features via Generalized Eigenvectors
• Deep learning for subgrid-scale turbulence modeling in large-eddy simulations of the atmospheric boundary layer
• Can Taxonomy Help? Improving Semantic Question Matching using Question Taxonomy
• Lifelong Learning of Compositional Structures
• Towards Learning Convolutions from Scratch
• Contextual Dropout: An Efficient Sample-Dependent Dropout Module
• Arabic Multi-Dialect Segmentation: bi-LSTM-CRF vs. SVM
• Neural Architectures for Fine-grained Entity Type Classification
• Joint Training Deep Boltzmann Machines for Classification
• Abstract Learning via Demodulation in a Deep Neural Network
• Fashion Retail: Forecasting Demand for New Items
• DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks
• Achieving Guidance in Applied Machine Learning through Software Engineering Techniques
• Deep Learning Neural Networks for Emotion Classification from Text: Enhanced Leaky Rectified Linear Unit Activation and Weighted Loss
• LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing
• Revisiting Spatial Invariance with Low-Rank Local Connectivity
• WEnets: A Convolutional Framework for Evaluating Audio Waveforms
• From genome to phenome: Predicting multiple cancer phenotypes based on somatic genomic alterations via the genomic impact transformer
• Adversarial Removal of Demographic Attributes from Text Data
• Entity Commonsense Representation for Neural Abstractive Summarization
• Structured Convolution Matrices for Energy-efficient Deep learning
• Bayesian Dropout
• Learning High-level Image Representation for Image Retrieval via Multi-Task DNN using Clickthrough Data
• Prediction of breast cancer recurrence using Classification Restricted Boltzmann Machine with Dropping
• SIDE-real: Supernova Ia Dust Extinction with truncated marginal neural ratio estimation applied to real data
• Learning in the Machine: Random Backpropagation and the Deep Learning Channel
• Which Contrast Does Matter? Towards a Deep Understanding of MR Contrast using Collaborative GAN
• On Dropout and Nuclear Norm Regularization
• Bidirectional Attention for SQL Generation
• Machine Learning's Dropout Training is Distributionally Robust Optimal
• Detecting Epileptic Seizures from EEG Data using Neural Networks
• Playing to distraction: towards a robust training of CNN classifiers through visual explanation techniques
• Improved Deep Convolutional Neural Network For Online Handwritten Chinese Character Recognition using Domain-Specific Knowledge
• Character-level Chinese Writer Identification using Path Signature Feature, DropStroke and Deep CNN
• Leveraging Uncertainty for Improved Static Malware Detection Under Extreme False Positive Constraints
• Principal Sensitivity Analysis
• OCoR: An Overlapping-Aware Code Retriever
• Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages
• Temporal Autoencoding Restricted Boltzmann Machine
• Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles
• A Simple LSTM model for Transition-based Dependency Parsing
• Automatic Fused Multimodal Deep Learning for Plant Identification
• An Analysis of the Connections Between Layers of Deep Neural Networks
• Parton distribution functions
• Automated Detecting and Placing Road Objects from Street-level Images
• Dropout is a special case of the stochastic delta rule: faster and more accurate deep learning
• Reducing the dilution: An analysis of the information sensitiveness of capsule network with a practical improvement method
• Multi-scale Orderless Pooling of Deep Convolutional Activation Features
• Joint Aspect and Polarity Classification for Aspect-based Sentiment Analysis with End-to-End Neural Networks
• Deep Recurrent Neural Network for Mobile Human Activity Recognition with High Throughput
• A Batched Scalable Multi-Objective Bayesian Optimization Algorithm
• Deep Learning the Indus Script
• SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives
• Large Scale Business Discovery from Street Level Imagery
• Enhancing Scientific Papers Summarization with Citation Graph
• Surface Defect Classification in Real-Time Using Convolutional Neural Networks
• Plasticity-rigidity cycles: A general adaptation mechanism
• UAV-assisted Distributed Learning for Environmental Monitoring in Rural Environments
• Iterative Low-Rank Approximation for CNN Compression
• Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks
• Secure Watermark for Deep Neural Networks with Multi-task Learning
• Transformed ${\ell }_1$ Regularization for Learning Sparse Deep Neural Networks
• Structured Pruning for Efficient ConvNets via Incremental Regularization
• MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
• Orthogonal Deep Neural Networks
• Incremental Parsing with Minimal Features Using Bi-Directional LSTM
• Context Aware Machine Learning
• CoMuTe: A Convolutional Neural Network Based Device Free Multiple Target Localization Using CSI
• Ordinal Pooling Networks: For Preserving Information over Shrinking Feature Maps
• On the Reduction of Variance and Overestimation of Deep Q-Learning
• How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?
• Data Stream Stabilization for Optical Coherence Tomography Volumetric Scanning
• Data Augmentation for Bayesian Deep Learning
• Character-Level Language Modeling with Hierarchical Recurrent Neural Networks
• Demand Forecasting using Long Short-Term Memory Neural Networks
• Word and Document Embeddings based on Neural Network Approaches
• Fiedler Regularization: Learning Neural Networks with Graph Sparsity
• Event Selection and Background Rejection in Time Projection Chambers Using Convolutional Neural Networks and a Specific Application to the AdEPT Gamma-ray Polarimeter Mission
• The ones that got away: chemical tagging of globular cluster-origin stars with Gaia BP/RP spectra
• Interpreting and Boosting Dropout from a Game-Theoretic View
• CIFAR-10: KNN-based Ensemble of Classifiers
• Fast and Accurate Person Re-Identification with RMNet
• Learning Fine-grained Features via a CNN Tree for Large-scale Classification
• Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers
• Densely Connected Recurrent Residual (Dense R2UNet) Convolutional Neural Network for Segmentation of Lung CT Images
• Bayesian Neural Networks at Scale: A Performance Analysis and Pruning Study
• Latent Model Ensemble with Auto-localization
• Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks
• Sparsifying Neural Network Connections for Face Recognition
• Merging External Bilingual Pairs into Neural Machine Translation
• Learned versus Hand-Designed Feature Representations for 3d Agglomeration
• Constraint-Based Regularization of Neural Networks
• The Three Hundred Project: Mapping The Matter Distribution in Galaxy Clusters Via Deep Learning from Multiview Simulated Observations
• Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
• Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
• Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction
• Bidirectional LSTM-CRF Attention-based Model for Chinese Word Segmentation
• Dependency Sensitive Convolutional Neural Networks for Modeling Sentences and Documents
• Automatic Assessment of the Design Quality of Python Programs with Personalized Feedback
• Prediction of Ultrasonic Guided Wave Propagation in Solid-fluid and their Interface under Uncertainty using Machine Learning
• Deep learning approach in multi-scale prediction of turbulent mixing-layer
• Neural Named Entity Recognition from Subword Units
• Near Real-time Hippocampus Segmentation Using Patch-based Canonical Neural Network
• A Scale Mixture Perspective of Multiplicative Noise in Neural Networks
• FR-Detect: A Multi-Modal Framework for Early Fake News Detection on Social Media Using Publishers Features
• Learning Phrase Embeddings from Paraphrases with GRUs
• Almost Sure Convergence of Dropout Algorithms for Neural Networks
• Neural Fine-Grained Entity Type Classification with Hierarchy-Aware Loss
• On the Depth of Deep Neural Networks: A Theoretical View
• Strategies for Conceptual Change in Convolutional Neural Networks
• From Maxout to Channel-Out: Encoding Information on Sparse Pathways
• Measuring Dependence with Matrix-based Entropy Functional
• Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling
• On the Inference Calibration of Neural Machine Translation
• Deep Neural Networks for Choice Analysis: Extracting Complete Economic Information for Interpretation
• Function Norms and Regularization in Deep Networks
• Autocorrect in the Process of Translation -- Multi-task Learning Improves Dialogue Machine Translation
• Avoiding overfitting of multilayer perceptrons by training derivatives
• Deep Boltzmann Machines in Estimation of Distribution Algorithms for Combinatorial Optimization
• Progressive and Aligned Pose Attention Transfer for Person Image Generation
• NLS: an accurate and yet easy-to-interpret regression method
• Rectified Factor Networks
• Scene Change Detection Using Multiscale Cascade Residual Convolutional Neural Networks
• Capacity Control of ReLU Neural Networks by Basis-path Norm
• Automated Polysomnography Analysis for Detection of Non-Apneic and Non-Hypopneic Arousals using Feature Engineering and a Bidirectional LSTM Network
• Exploiting the Statistics of Learning and Inference
• Light-Weighted CNN for Text Classification
• Radar Emitter Classification with Attribute-specific Recurrent Neural Networks
• Scalable and Incremental Learning of Gaussian Mixture Models
• Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks
• A Cross-Domain Transferable Neural Coherence Model
• Divide and Conquer: A Deep CASA Approach to Talker-independent Monaural Speaker Separation
• HEp-2 Cell Image Classification with Deep Convolutional Neural Networks
• Automatic Post-Editing for Machine Translation
• Ensemble Soft-Margin Softmax Loss for Image Classification
• Efficient Hardware Realization of Convolutional Neural Networks using Intra-Kernel Regular Pruning
• Learning Discriminative Features via Label Consistent Neural Network
• Going Wider: Recurrent Neural Network With Parallel Cells
• Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition
• An Improved Deep Belief Network Model for Road Safety Analyses
• Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification
• Enhancing Operation of a Sewage Pumping Station for Inter Catchment Wastewater Transfer by Using Deep Learning and Hydraulic Model
• Piecewise Linear Multilayer Perceptrons and Dropout
• Instant Learning: Parallel Deep Neural Networks and Convolutional Bootstrapping
• Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification
• TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks
• Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
• Invariant backpropagation: how to train a transformation-invariant neural network
• Deep RNN Framework for Visual Sequential Applications
• Scene Labeling with Contextual Hierarchical Models
• CCL: Cross-modal Correlation Learning with Multi-grained Fusion by Hierarchical Network
• A Feature Fusion-Net Using Deep Spatial Context Encoder and Nonstationary Joint Statistical Model for High Resolution SAR Image Classification
• Improving random walk rankings with feature selection and imputation
• Open DNN Box by Power Side-Channel Attack
• Dither is Better than Dropout for Regularising Deep Neural Networks
• Automatic selection of active spaces for strongly correlated systems using machine learning algorithms
• Compression of Fully-Connected Layer in Neural Network by Kronecker Product
• Point Cloud Audio Processing
• End-to-End Text Classification via Image-based Embedding using Character-level Networks
• Thoughts on a Recursive Classifier Graph: a Multiclass Network for Deep Object Recognition
• Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners
• $N^4$-Fields: Neural Network Nearest Neighbor Fields for Image Transforms
• Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module
• Simplified Stochastic Feedforward Neural Networks
• The Benefit of the Doubt: Uncertainty Aware Sensing for Edge Computing Platforms
• Automatic Extraction of Secrets from the Transistor Jungle using Laser-Assisted Side-Channel Attacks
• A Study of Gender Classification Techniques Based on Iris Images: A Deep Survey and Analysis
• Learning Optimal Data Augmentation Policies via Bayesian Optimization for Image Classification Tasks
• An Intelligent Approach to Detecting Novel Fault Classes for Centrifugal Pumps Based on Deep CNNs and Unsupervised Methods
• Marginalizing Corrupted Features
• Autoencoder Regularized Network For Driving Style Representation Learning
• Neural Network Regularization via Robust Weight Factorization
• Improving Neural Network Generalization by Combining Parallel Circuits with Dropout
• Gaussian Process Neurons Learn Stochastic Activation Functions
• Accelerate CNN via Recursive Bayesian Pruning
• Query-adaptive Image Retrieval by Deep Weighted Hashing
• LDMNet: Low Dimensional Manifold Regularized Neural Networks
• Detecting Dead Weights and Units in Neural Networks
• Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
• Enhancing the Regularization Effect of Weight Pruning in Artificial Neural Networks
• Automatic Photo Adjustment Using Deep Neural Networks
• Unsupervised Regenerative Learning of Hierarchical Features in Spiking Deep Networks for Object Recognition
• Deep Multi-task Learning for Railway Track Inspection
• Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph
• Machine Learning Automation Toolbox (MLaut)
• Chinese-Portuguese Machine Translation: A Study on Building Parallel Corpora from Comparable Texts
• Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
• Learning-accelerated A* Search for Risk-aware Path Planning
• MHAttnSurv: Multi-Head Attention for Survival Prediction Using Whole-Slide Pathology Images
• Knowledge Graph Embedding with Atrous Convolution and Residual Learning
• DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition
• $\mathcal{G}$-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space
• Multi-Loss Sub-Ensembles for Accurate Classification with Uncertainty Estimation
• Reconstruction for Powerful Graph Representations
• HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Network
• Prediction intervals for Deep Neural Networks
• Combine Convolution with Recurrent Networks for Text Classification
• Defending Adversarial Attacks by Correcting logits
• Generating Person Images with Appearance-aware Pose Stylizer
• Dropout Rademacher Complexity of Deep Neural Networks
• Consumer Behaviour in Retail: Next Logical Purchase using Deep Neural Network
• Understanding Dropout: Training Multi-Layer Perceptrons with Auxiliary Independent Stochastic Neurons
• Coloring the Black Box: Visualizing neural network behavior with a self-introspective model
• Financial Time Series Prediction Using Deep Learning
• Learning Fine-grained Fact-Article Correspondence in Legal Cases
• WeightNet: Revisiting the Design Space of Weight Networks
• Abusive Language Detection and Characterization of Twitter Behavior
• Research Progress of Convolutional Neural Network and its Application in Object Detection
• Investigating the Relationship Between Dropout Regularization and Model Complexity in Neural Networks
• Document-level Neural Machine Translation with Document Embeddings
• Neural Machine Translation with Source-Side Latent Graph Parsing
• ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation
• End-to-End Text-Dependent Speaker Verification
• Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings
• Branch-Cooperative OSNet for Person Re-Identification
• Matching Handwritten Document Images
• Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method
• On the Equivalence Between Deep NADE and Generative Stochastic Networks
• Safety of Quark/Gluon Jet Classification
• Multiple Range-Restricted Bidirectional Gated Recurrent Units with Attention for Relation Classification
• A novel combination of theoretical analysis and data-driven method for reconstruction of structural defects
• A Deep Neural Architecture for Sentence-level Sentiment Classification in Twitter Social Networking
• Learning a Generator Model from Terminal Bus Data
• Neural Aesthetic Image Reviewer
• Fast Adaptive Weight Noise
• Deep Networks with Fast Retraining
• Multi-Mention Learning for Reading Comprehension with Neural Cascades
• Learning Compact Convolutional Neural Networks with Nested Dropout
• Maxmin convolutional neural networks for image classification
• Conditional independence testing: a predictive perspective
• DTMT: A Novel Deep Transition Architecture for Neural Machine Translation
• Topic Identification for Speech without ASR
• PhytNet -- Tailored Convolutional Neural Networks for Custom Botanical Data
• Temporal Collaborative Ranking Via Personalized Transformer
• Learning by Design: Structuring and Documenting the Human Choices in Machine Learning Development
• Attention Transfer Network for Aspect-level Sentiment Classification
• GradNets: Dynamic Interpolation Between Neural Architectures
• Robust Deep Graph Based Learning for Binary Classification
• Self-Orthogonality Module: A Network Architecture Plug-in for Learning Orthogonal Filters
• Multilevel Context Representation for Improving Object Recognition
• A new way to constrain the densities of intra-group medium in groups of galaxies with convolutional neural networks
• FLFE: A Communication-Efficient and Privacy-Preserving Federated Feature Engineering Framework
• Differentially Private Variational Dropout
• Denoising Autoencoders for fast Combinatorial Black Box Optimization
• Learning Sparse Deep Feedforward Networks via Tree Skeleton Expansion
• Locally Smoothed Neural Networks
• Learning Machines Implemented on Non-Deterministic Hardware
• Less-forgetful Learning for Domain Expansion in Deep Neural Networks
• Can deep learning help you find the perfect match?
• Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction
• Proprioceptive Robot Collision Detection through Gaussian Process Regression
• Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks
• Hidden Markov Neural Networks
• AMSI-Based Detection of Malicious PowerShell Code Using Contextual Embeddings
• GraphConnect: A Regularization Framework for Neural Networks
• Weakly supervised learning for pattern classification in serial femtosecond crystallography
• Stochastic Model Pruning via Weight Dropping Away and Back
• Informed Machine Learning, Centrality, CNN, Relevant Document Detection, Repatriation of Indigenous Human Remains
• Dynamic Graph Modules for Modeling Object-Object Interactions in Activity Recognition
• Deep Probabilistic Ensembles: Approximate Variational Inference through KL Regularization
• Surprising properties of dropout in deep networks
• Predicting TED Talk Ratings from Language and Prosody
• "Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training Deep Neural Networks
• Packet-Loss-Tolerant Split Inference for Delay-Sensitive Deep Learning in Lossy Wireless Networks
• Effective Feature Representation for Clinical Text Concept Extraction
• Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks
• What training reveals about neural network complexity
• A Multi-Level Attention Model for Evidence-Based Fact Checking
• An ETF view of Dropout regularization
• Who Blames Whom in a Crisis? Detecting Blame Ties from News Articles Using Neural Networks
• The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression
• Recycle deep features for better object detection
• Regularizing Recurrent Networks - On Injected Noise and Norm-based Methods
• Supervised Deep Sparse Coding Networks
• Top-1 Solution of Multi-Moments in Time Challenge 2019
• Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field
• Two Dimensional Stochastic Configuration Networks for Image Data Analytics
• GSNs : Generative Stochastic Networks
• On the achievability of blind source separation for high-dimensional nonlinear source mixtures
• Deep Learning Parametrization for B-Spline Curve Approximation
• Solving inverse problems with deep neural networks driven by sparse signal decomposition in a physics-based dictionary
• Neural Architectures for Named Entity Recognition
• An optimized system to solve text-based CAPTCHA
• Uncertainty Quantification of Locally Nonlinear Dynamical Systems using Neural Networks
• Improved Image Augmentation for Convolutional Neural Networks by Copyout and CopyPairing
• Image aesthetic evaluation using paralleled deep convolution neural network
• Clothing Retrieval with Visual Attention Model
• CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble Behavior
• Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition
• Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild
• Delving Deep into Liver Focal Lesion Detection: A Preliminary Study
• Unsupervised detection and open-set classification of fast-ramped flexibility activation events
• Deep Data Flow Analysis
• Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs
• MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization
• A simple and effective postprocessing method for image classification
• Learning Light-Weight Translation Models from Deep Transformer
• Neuron with Steady Response Leads to Better Generalization
• Mocking Faint Black Holes during Reionization
• Analysis of skin lesion images with deep learning
• Dropout as a Regularizer of Interaction Effects
• Entity Candidate Network for Whole-Aware Named Entity Recognition
• Machine Learning Approach to Earthquake Rupture Dynamics
• Decoupling Inherent Risk and Early Cancer Signs in Image-based Breast Cancer Risk Models
• Fine-tuning Handwriting Recognition systems with Temporal Dropout
• Variational inference of latent state sequences using Recurrent Networks
• Classification of Breast Cancer Lesions in Ultrasound Images by using Attention Layer and loss Ensembles in Deep Convolutional Neural Networks
• Deconfusing intensity maps with neural networks
• Routing Towards Discriminative Power of Class Capsules
• Deep Learning for Distributed Channel Feedback and Multiuser Precoding in FDD Massive MIMO
• Structured Dropout Variational Inference for Bayesian Neural Networks
• Table-Of-Contents generation on contemporary documents
• Pre-interpolation loss behaviour in neural networks
• Applying Deep Machine Learning for psycho-demographic profiling of Internet users using O.C.E.A.N. model of personality
• Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability
• Differential equations as models of deep neural networks
• Inherent Weight Normalization in Stochastic Neural Networks
• A Capsule-unified Framework of Deep Neural Networks for Graphical Programming
• Efficient Estimation of Influence of a Training Instance
• Improving compute efficacy frontiers with SliceOut
• Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning
• Compiler-Guided Throughput Scheduling for Many-core Machines
• Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization
• Lexical Translation Model Using a Deep Neural Network Architecture
• Rapid Elastic Architecture Search under Specialized Classes and Resource Constraints
• Patch-level Neighborhood Interpolation: A General and Effective Graph-based Regularization Strategy
• Monte Carlo dropout increases model repeatability
• Estimating uncertainty of earthquake rupture using Bayesian neural network
• Investigation of Training Label Error Impact on RNN-T
• Extracting and Learning a Dependency-Enhanced Type Lexicon for Dutch
• Training Deep Neural Networks by optimizing over nonlocal paths in hyperparameter space
• Deep Neural Networks for Choice Analysis: Architectural Design with Alternative-Specific Utility Functions
• Deep set conditioned latent representations for action recognition
• Copy-Enhanced Heterogeneous Information Learning for Dialogue State Tracking
• Dual-FOFE-net Neural Models for Entity Linking with PageRank
• PULASki: Learning inter-rater variability using statistical distances to improve probabilistic segmentation
• Unsupervised End-to-End Training with a Self-Defined Target
• Machine-learning-enabled characterization of individual ring resonators in integrated photonic lattices
• Connections Between Pairs of Filters Improve the Accuracy of Convolutional Neural Networks
• A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification
• Reconstruction of Natural Visual Scenes from Neural Spikes with Deep Neural Networks
• A Package for the Automated Classification of Images Containing Supernova Light Echoes
• Livewired Neural Networks: Making Neurons That Fire Together Wire Together
• Analysing Dropout and Compounding Errors in Neural Language Models
• Variational Bayesian Dropout with a Hierarchical Prior
• Learning Negotiating Behavior Between Cars in Intersections using Deep Q-Learning
• SCONE: Supernova Classification with a Convolutional Neural Network
• A Template-guided Hybrid Pointer Network for Knowledge-basedTask-oriented Dialogue Systems
• Building Context-aware Clause Representations for Situation Entity Type Classification
• Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction
• A Convolutional Neural Network for Aspect Sentiment Classification
• BayesGrad: Explaining Predictions of Graph Convolutional Networks
• Semi-supervised Learning for Marked Temporal Point Processes
• Towards Controlled and Diverse Generation of Article Comments
• A Joint and Domain-Adaptive Approach to Spoken Language Understanding
• Learning to rank for censored survival data
• Backdrop: Stochastic Backpropagation
• The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation
• DeepEmo: Learning and Enriching Pattern-Based Emotion Representations
• A Novel Geometric Approach for Outlier Recognition in High Dimension
• Disturbing Target Values for Neural Network Regularization
• Field-Programmable Deep Neural Network (DNN) Learning and Inference accelerator: a concept
• Out-distribution training confers robustness to deep neural networks
• Rethinking the Value of Transformer Components
• Generalized Constraints as A New Mathematical Problem in Artificial Intelligence: A Review and Perspective
• Cascade Attentive Dropout for Weakly Supervised Object Detection
• Comparing methods addressing multi-collinearity when developing prediction models
• Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning
• Construction of a far ultraviolet all sky map from an incomplete survey: Application of a deep learning algorithm
• Is the User Enjoying the Conversation? A Case Study on the Impact on the Reward Function
• Deep learning bank distress from news and numerical financial data
• Training Image Selection using Recurrent Neural Networks: An Application in Hydrogeology
• Optical Convolutional Neural Networks -- Combining Silicon Photonics and Fourier Optics for Computer Vision
• Learning in Deep Neural Networks Using a Biologically Inspired Optimizer
• Stochastic Bottleneck: Rateless Auto-Encoder for Flexible Dimensionality Reduction
• Adma: A Flexible Loss Function for Neural Networks
• Adversarial Robustness for Machine Learning Cyber Defenses Using Log Data
• Neural Neighborhood Encoding for Classification
• Convolution in Convolution for Network in Network
• Zero-Shot Human-Object Interaction Recognition via Affordance Graphs
• Significance Driven Hybrid 8T-6T SRAM for Energy-Efficient Synaptic Storage in Artificial Neural Networks
• On Study of the Binarized Deep Neural Network for Image Classification
• Fused Deep Convolutional Neural Network for Precision Diagnosis of COVID-19 Using Chest X-Ray Images
• Maximum Entropy Binary Encoding for Face Template Protection
• Feature-Level Domain Adaptation
• Latent Opinions Transfer Network for Target-Oriented Opinion Words Extraction
• Advances in Collaborative Filtering and Ranking
• Automatic Whole-body Bone Age Assessment Using Deep Hierarchical Features
• Using multi-task learning to improve the performance of acoustic-to-word and conventional hybrid models
• Leveraging Newswire Treebanks for Parsing Conversational Data with Argument Scrambling
• A Multilingual Encoding Method for Text Classification and Dialect Identification Using Convolutional Neural Network
• Learning Shared Encoding Representation for End-to-End Speech Recognition Models
• Benchmarking Approximate Inference Methods for Neural Structured Prediction
• Deep Haar Scattering Networks
• DeepWriterID: An End-to-end Online Text-independent Writer Identification System
• Adaptive Weighting Depth-variant Deconvolution of Fluorescence Microscopy Images with Convolutional Neural Network
• Discontinuous Piecewise Polynomial Neural Networks
• A Weakly Supervised Approach to Train Temporal Relation Classifiers and Acquire Regular Event Pairs Simultaneously
• Tikhonov Regularization for Long Short-Term Memory Networks
• Closing the loop between neural network simulators and the OpenAI Gym
• Learning event representation: As sparse as possible, but not sparser
• A Multichannel Convolutional Neural Network For Cross-language Dialog State Tracking
• Deep Collaborative Learning for Visual Recognition
• GIM: Gaussian Isolation Machines
• Predicting Toxicity from Gene Expression with Neural Networks
• Itsy Bitsy SpiderNet: Fully Connected Residual Network for Fraud Detection
• Strategies for Robust Image Classification
• Only sparsity based loss function for learning representations
• Adaptive Hierarchical Decomposition of Large Deep Networks
• Sparse, guided feature connections in an Abstract Deep Network
• Deep Representation with ReLU Neural Networks
• Recent Advances in Large Margin Learning
• Deep Transform: Time-Domain Audio Error Correction via Probabilistic Re-Synthesis
• C2G-Net: Exploiting Morphological Properties for Image Classification
• Shakeout: A New Approach to Regularized Deep Neural Network Training
• Estimating galaxy masses from kinematics of globular cluster systems: a new method based on deep learning
• A New Training Method for Feedforward Neural Networks Based on Geometric Contraction Property of Activation Functions
• Deep Learning-based Stress Determinator for Mouse Psychiatric Analysis using Hippocampus Activity
• Sequential Feature Filtering Classifier
• What needles do sparse neural networks find in nonlinear haystacks
• Using Context Information to Enhance Simple Question Answering
• AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification
• Towards Robust Classification with Image Quality Assessment
• Crossover-Net: Leveraging the Vertical-Horizontal Crossover Relation for Robust Segmentation
• Development of digitally obtainable 10-year risk scores for depression and anxiety in the general population
• Beyond Short Clips: End-to-End Video-Level Learning with Collaborative Memories
• Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search
• Dropout Training for SVMs with Data Augmentation
• Efficient Sparse Artificial Neural Networks
• Unifying the Stochastic Spectral Descent for Restricted Boltzmann Machines with Bernoulli or Gaussian Inputs
• Enhanced Aspect-Based Sentiment Analysis Models with Progressive Self-supervised Attention Learning
• RoutingGAN: Routing Age Progression and Regression with Disentangled Learning
• Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation
• Open-domain Topic Identification of Out-of-domain Utterances using Wikipedia
• Reinforced Temporal Attention and Split-Rate Transfer for Depth-Based Person Re-Identification
• Mixture separability loss in a deep convolutional network for image classification
• End-to-End Chinese Parsing Exploiting Lexicons
• Improved Training for Self-Training by Confidence Assessments
• Conditional Generative Adversarial Networks for Optimal Path Planning
• Multilingual Adaptation of RNN Based ASR Systems
• Predicting Gene Expression Between Species with Neural Networks
• Generating Diverse Translation from Model Distribution with Dropout
• Optimized Sharing of Coefficients in Parallel Filter Banks
• Graph Interpolating Activation Improves Both Natural and Robust Accuracies in Data-Efficient Deep Learning
• Application of Facial Recognition using Convolutional Neural Networks for Entry Access Control
• Convergence Analysis of Homotopy-SGD for non-convex optimization
• Two-Stream Appearance Transfer Network for Person Image Generation
• Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation
• Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language
• Semi-Supervised Learning with Meta-Gradient
• Activation Map Adaptation for Effective Knowledge Distillation
• A Greedy Algorithm for Quantizing Neural Networks
• Topical Behavior Prediction from Massive Logs
• Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition
• ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
• Exponential Discriminative Metric Embedding in Deep Learning
• Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos
• How to boost autoencoders?
• Self-Supervision and Spatial-Sequential Attention Based Loss for Multi-Person Pose Estimation
• Broad Learning for Healthcare
• Image Disguise based on Generative Model
• Multi-concept adversarial attacks
• Token Drop mechanism for Neural Machine Translation
• Optimizing Neural Network for Computer Vision task in Edge Device
• Turning old models fashion again: Recycling classical CNN networks using the Lattice Transformation
• Using Context Events in Neural Network Models for Event Temporal Status Identification
• Active Learning for Argument Mining: A Practical Approach
• Incorporating Chinese Radicals Into Neural Machine Translation: Deeper Than Character Level
• Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP
• Out-of-Distribution Example Detection in Deep Neural Networks using Distance to Modelled Embedding
• Multi-task learning of daily work and study round-trips from survey data
• Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking
• Towards Lower-Dose PET using Physics-Based Uncertainty-Aware Multimodal Learning with Robustness to Out-of-Distribution Data
• Dropout Regularization for Self-Supervised Learning of Transformer Encoder Speech Representation
• Pseudo-positive regularization for deep person re-identification
• Block-Cyclic Stochastic Coordinate Descent for Deep Neural Networks
• Generalization by design: Shortcuts to Generalization in Deep Learning
• Leveraging Medical Sentiment to Understand Patients Health on Social Media
• Structured in Space, Randomized in Time: Leveraging Dropout in RNNs for Efficient Training
• A Distributed Deep Representation Learning Model for Big Image Data Classification
• CODA: Constructivism Learning for Instance-Dependent Dropout Architecture Construction
• Object-sensitive Deep Reinforcement Learning
• Geometric Neural Phrase Pooling: Modeling the Spatial Co-occurrence of Neurons
• A Byte-sized Approach to Named Entity Recognition
• Regularization in ResNet with Stochastic Depth
• Reconciling Feature-Reuse and Overfitting in DenseNet with Specialized Dropout
• Horn: A System for Parallel Training and Regularizing of Large-Scale Neural Networks
• Multi-scale Convolution Aggregation and Stochastic Feature Reuse for DenseNets
• Estimating air quality co-benefits of energy transition using machine learning
• Targeted Deep Learning: Framework, Methods, and Applications
• Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach
• FINNger -- Applying artificial intelligence to ease math learning for children
• Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation
• Randomness and Interpolation Improve Gradient Descent
• Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model
• A Joint Model for Aspect-Category Sentiment Analysis with Shared Sentiment Prediction Layer
• Self-Balanced Dropout
• Inverse Structural Design of Graphene/Boron Nitride Hybrids by Regressional GAN
• A Morpho-Syntactically Informed LSTM-CRF Model for Named Entity Recognition
• Deep Learning for Estimating Synaptic Health of Primary Neuronal Cell Culture
• Dual Attention Model for Citation Recommendation
• Transfer Learning Between Related Tasks Using Expected Label Proportions
• Search Intelligence: Deep Learning For Dominant Category Prediction
• Use Generalized Representations, But Do Not Forget Surface Features
• Population Gradients improve performance across data-sets and architectures in object classification
• DropRegion Training of Inception Font Network for High-Performance Chinese Font Recognition
• Continuous Learning: Engineering Super Features With Feature Algebras
• One Model to Learn Both: Zero Pronoun Prediction and Translation
• Estimating Fingertip Forces, Torques, and Local Curvatures from Fingernail Images
• Document-level Neural Machine Translation with Associated Memory Network
• Invexifying Regularization of Non-Linear Least-Squares Problems
• Quaternion-Based Graph Convolution Network for Recommendation
• Patch-based Medical Image Segmentation using Matrix Product State Tensor Networks
• Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness
• Bayesian Sparsification Methods for Deep Complex-valued Networks
• Recognition Confidence Analysis of Handwritten Chinese Character with CNN
• Belief Flows of Robust Online Learning
• Weight mechanism: adding a constant in concatenation of series connect
• The Long-Short Story of Movie Description
• GPCA: A Probabilistic Framework for Gaussian Process Embedded Channel Attention
• Deep Learning-Based Image Kernel for Inductive Transfer
• Diabetic Retinopathy detection by retinal image recognizing
• Analysis of Video Feature Learning in Two-Stream CNNs on the Example of Zebrafish Swim Bout Classification
• RotationOut as a Regularization Method for Neural Network
• Think Global, Act Local: Relating DNN generalisation and node-level SNR
• Convolutional Architecture Exploration for Action Recognition and Image Classification
• The effects of regularisation on RNN models for time series forecasting: Covid-19 as an example
• HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression
• Regularizing Neural Networks via Stochastic Branch Layers
• Quantal synaptic dilution enhances sparse encoding and dropout regularisation in deep networks
• LFGCN: Levitating over Graphs with Levy Flights
• Teaching a Machine to Diagnose a Heart Disease; Beginning from digitizing scanned ECGs to detecting the Brugada Syndrome (BrS)
• Learning Connectivity of Neural Networks from a Topological Perspective
• A deep learning approach to the structural analysis of proteins
• Empirical study of PROXTONE and PROXTONE${}^{+}$ for Fast Learning of Large Scale Sparse Models
• Supervised Learning in Temporally-Coded Spiking Neural Networks with Approximate Backpropagation
• Stochastic Function Norm Regularization of Deep Networks