# Downloads 2018

Number of events: 541

- 3D-FilterMap: A Compact Architecture for Deep Convolutional Neural Networks
- 3D-Scene-GAN: Three-dimensional Scene Reconstruction with Generative Adversarial Networks
- A Bayesian Perspective on Generalization and Stochastic Gradient Descent
- Accelerating Neural Architecture Search using Performance Prediction
- A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs
- Action-dependent Control Variates for Policy Optimization via Stein Identity
- Activation Maximization Generative Adversarial Nets
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Active Neural Localization
- Adapting to Continuously Shifting Domains
- Adaptive Dropout with Rademacher Complexity Regularization
- Adaptive Memory Networks
- Adaptive Path-Integral Approach for Representation Learning and Planning
- Adaptive Quantization of Neural Networks
- A Dataset To Evaluate The Representations Learned By Video Prediction Models
- Additive Margin Softmax for Face Verification
- A Deep Reinforced Model for Abstractive Summarization
- A differentiable BLEU loss. Analysis and first results
- A DIRT-T Approach to Unsupervised Domain Adaptation
- Adversarial Dropout Regularization
- Adversarial Policy Gradient for Alternating Markov Games
- Adversarial Spheres
- A Flexible Approach to Automated RNN Architecture Generation
- A Framework for the Quantitative Evaluation of Disentangled Representations
- A Hierarchical Model for Device Placement
- A Language and Compiler View on Differentiable Programming
- All-but-the-Top: Simple and Effective Postprocessing for Word Representations
- Alternating Multi-bit Quantization for Recurrent Neural Networks
- AmbientGAN: Generative models from lossy measurements
- A moth brain learns to read MNIST
- Analysis of Cosmic Microwave Background with Deep Learning
- Analyzing and Exploiting NARX Recurrent Neural Networks for Long-Term Dependencies
- An efficient framework for learning sentence representations
- A Neural Network Model That Can Reason
- A Neural Representation of Sketch Drawings
- An Evaluation of Fisher Approximations Beyond Kronecker Factorization
- A New Method of Region Embedding for Text Classification
- An Experimental Study of Neural Networks for Variable Graphs
- An image representation based convolutional network for DNA classification
- An interpretable LSTM neural network for autoregressive exogenous model
- An Online Learning Approach to Generative Adversarial Networks
- An Optimization View on Dynamic Routing Between Capsules
- A PAC-Bayesian Approach to Spectrally-Normalized Margin Bounds for Neural Networks
- Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy
- A Proximal Block Coordinate Descent Algorithm for Deep Neural Network Training
- Are Efficient Deep Representations Learnable?
- A Scalable Laplace Approximation for Neural Networks
- A Simple Neural Attentive Meta-Learner
- Ask the Right Questions: Active Question Reformulation with Reinforcement Learning
- Aspect-based Question Generation
- Attacking Binarized Neural Networks
- Attacking the Madry Defense Model with $L_1$-based Adversarial Examples
- Augmenting Clinical Intellgence with Machine Intelligence
- Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis
- Auto-Encoding Sequential Monte Carlo
- AUTOMATED DESIGN USING NEURAL NETWORKS AND GRADIENT DESCENT
- Automatically Inferring Data Quality for Spatiotemporal Forecasting
- Autoregressive Generative Adversarial Networks
- Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
- Bayesian Incremental Learning for Deep Neural Networks
- Benefits of Depth for Long-Term Memory of Recurrent Networks
- Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
- Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering
- Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
- Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
- Black-box Attacks on Deep Neural Networks via Gradient Estimation
- Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions
- Boosting the Actor with Dual Critic
- Boundary Seeking GANs
- Breaking the Softmax Bottleneck: A High-Rank RNN Language Model
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Can Deep Reinforcement Learning solve Erdos-Selfridge-Spencer Games?
- Can Neural Networks Understand Logical Entailment?
- Can recurrent neural networks warp time?
- Capturing Human Category Representations by Sampling in Deep Feature Spaces
- Cascade Adversarial Machine Learning Regularized with a Unified Embedding
- Causal Discovery Using Proxy Variables
- CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training
- Censoring Representations with Multiple-Adversaries over Random Subspaces
- Certified Defenses against Adversarial Examples
- Certifying Some Distributional Robustness with Principled Adversarial Training
- cGANs with Projection Discriminator
- Challenges in Disentangling Independent Factors of Variation
- Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
- ChatPainter: Improving Text to Image Generation using Dialogue
- Clustering Meets Implicit Generative Models
- COLD FUSION: TRAINING SEQ2SEQ MODELS TOGETHER WITH LANGUAGE MODELS
- Combating Adversarial Attacks Using Sparse Representations
- Combining Symbolic Expressions and Black-box Function Evaluations in Neural Programs
- ComboGAN: Unrestricted Scalability for Image Domain Translation
- Communication Algorithms via Deep Learning
- Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks
- Compositional Attention Networks for Machine Reasoning
- Compositional Obverter Communication Learning from Raw Visual Input
- Compressing Word Embeddings via Deep Compositional Code Learning
- Compression by the signs: distributed learning is a two-way street
- Concept Learning with Energy-Based Models
- Conditional Networks for Few-Shot Semantic Segmentation
- Consequentialist conditional cooperation in social dilemmas with imperfect information
- Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
- Convolutional Sequence Modeling Revisited
- Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields
- Countering Adversarial Images using Input Transformations
- Coupled Ensembles of Neural Networks
- Covariant Compositional Networks For Learning Graphs
- Critical Percolation as a Framework to Analyze the Training of Deep Networks
- Critical Points of Linear Neural Networks: Analytical Forms and Landscape Properties
- DCN+: Mixed Objective And Deep Residual Coattention for Question Answering
- Debiasing Evidence Approximations: On Importance-weighted Autoencoders and Jackknife Variational Inference
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
- Decision Boundary Analysis of Adversarial Examples
- Decoding Decoders: Finding Optimal Representation Spaces for Unsupervised Similarity Tasks
- Decoupling Dynamics and Reward for Transfer Learning
- Decoupling the Layers in Residual Networks
- Deep Active Learning for Named Entity Recognition
- Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
- Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling
- Deep Complex Networks
- Deep Convolutional Malware Classifiers Can Learn from Raw Executables and Labels Only
- Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
- Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design
- Deep Learning as a Mixed Convex-Combinatorial Optimization Problem
- Deep Learning for Physical Processes: Incorporating Prior Scientific Knowledge
- Deep learning mutation prediction enables early stage lung cancer detection in liquid biopsy
- Deep Learning with Ensembles of Neocortical Microcircuits
- Deep Learning with Logged Bandit Feedback
- DeepNCM: Deep Nearest Class Mean Classifiers
- Deep Neural Maps
- Deep Neural Networks as Gaussian Processes
- Deep Rewiring: Training very sparse deep networks
- Deep Sensing: Active Sensing using Multi-directional Recurrent Neural Networks
- Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning
- Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models
- Demystifying MMD GANs
- Depth separation and weight-width trade-offs for sigmoidal neural networks
- Depthwise Separable Convolutions for Neural Machine Translation
- Designing Efficient Neural Attention Systems Towards Achieving Human-level Sharp Vision
- Detecting Statistical Interactions from Neural Network Weights
- DiCE: The Infinitely Differentiable Monte-Carlo Estimator
- Differentiable Neural Network Architecture Search
- Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
- Distributed Distributional Deterministic Policy Gradients
- Distributed Fine-tuning of Language Models on Private Data
- Distributed Prioritized Experience Replay
- Distributional Adversarial Networks
- Diversity-Driven Exploration Strategy for Deep Reinforcement Learning
- Divide and Conquer Networks
- Divide-and-Conquer Reinforcement Learning
- DLVM: A modern compiler infrastructure for deep learning systems
- DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images
- Do GANs learn the distribution? Some Theory and Empirics
- Don't Decay the Learning Rate, Increase the Batch Size
- DORA The Explorer: Directed Outreaching Reinforcement Action-Selection
- Dynamic Neural Program Embeddings for Program Repair
- Easing non-convex optimization with neural networks
- eCommerceGAN: A Generative Adversarial Network for e-commerce
- Efficient Entropy For Policy Gradient with Multi-Dimensional Action Space
- Efficient Recurrent Neural Networks using Structured Matrices in FPGAs
- Efficient Sparse-Winograd Convolutional Neural Networks
- Eigenoption Discovery through the Deep Successor Representation
- Emergence of grid-like representations by training recurrent neural networks to perform spatial localization
- Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
- Emergent Communication in a Multi-Modal, Multi-Step Referential Game
- Emergent Communication through Negotiation
- Emergent Complexity via Multi-Agent Competition
- Emergent Translation in Multi-Agent Communication
- Empirical Analysis of the Hessian of Over-Parametrized Neural Networks
- Empirical Risk Landscape Analysis for Understanding Deep Neural Networks
- Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks
- Ensemble Adversarial Training: Attacks and Defenses
- Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms
- Espresso: Efficient Forward Propagation for Binary Deep Neural Networks
- Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
- Evaluating visual "common sense" using fine-grained classification and captioning tasks
- Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
- Expert-based reward function training: the novel method to train sequence generators
- Exploring Deep Recurrent Models with Reinforcement Learning for Molecule Design
- Exponentially vanishing sub-optimal local minima in multilayer neural networks
- Expressive power of recurrent neural networks
- Extending Robust Adversarial Reinforcement Learning Considering Adaptation and Diversity
- Extending the Framework of Equilibrium Propagation to General Dynamics
- Fast and Accurate Reading Comprehension by Combining Self-Attention and Convolution
- Fast and Accurate Text Classification: Skimming, Rereading and Early Stopping
- Faster Discovery of Neural Architectures by Searching for Paths in a Large Model
- Faster Neural Networks Straight from JPEG
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- Fast Node Embeddings: Learning Ego-Centric Representations
- FearNet: Brain-Inspired Model for Incremental Learning
- Feature-Based Metrics for Exploring the Latent Space of Generative Models
- Feature Incay for Representation Regularization
- Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions
- Few-Shot Learning with Graph Neural Networks
- Fidelity-Weighted Learning
- FigureQA: An Annotated Figure Dataset for Visual Reasoning
- Finding Flatter Minima with SGD
- Fireside Chat with Daphne Koller
- Fix your classifier: the marginal value of training the last weight layer
- Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
- Fraternal Dropout
- From Generative Models to Generative Agents
- FusionNet: Fusing via Fully-aware Attention with Application to Machine Comprehension
- GANITE: Estimation of Individualized Treatment Effects using Generative Adversarial Nets
- Gaussian Process Behaviour in Wide Deep Neural Networks
- Generalizing Across Domains via Cross-Gradient Training
- Generalizing Hamiltonian Monte Carlo with Neural Networks
- Generating Natural Adversarial Examples
- Generating Wikipedia by Summarizing Long Sequences
- Generative Modeling for Protein Structures
- Generative Models of Visually Grounded Imagination
- Generative networks as inverse problems with Scattering transforms
- GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks
- GILBO: One Metric to Measure Them All
- GitGraph - from Computational Subgraphs to Smaller Architecture Search Spaces
- Global Optimality Conditions for Deep Neural Networks
- Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
- Gradient-based Optimization of Neural Network Architecture
- Gradient Estimators for Implicit Models
- Gradients explode - Deep Networks are shallow - ResNet explained
- Graph Attention Networks
- Graph Partition Neural Networks for Semi-Supervised Classification
- Guide Actor-Critic for Continuous Control
- HexaConv
- Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning
- Hierarchical Density Order Embeddings
- Hierarchical Representations for Efficient Architecture Search
- Hierarchical Subtask Discovery with Non-Negative Matrix Factorization
- Hockey-Stick GAN
- HoME: a Household Multimodal Environment
- Hyperparameter optimization: a spectral approach
- IamNN: Iterative and Adaptive Mobile Neural Network for efficient image classification
- Identifying Analogies Across Domains
- Imitation Learning from Visual Data with Multiple Intentions
- Implicit Causal Models for Genome-wide Association Studies
- Improving GANs Using Optimal Transport
- Improving GAN Training via Binarized Representation Entropy (BRE) Regularization
- Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
- Improving the Universality and Learnability of Neural Programmer-Interpreters with Combinator Abstraction
- Inference in probabilistic graphical models by Graph Neural Networks
- Initialization matters: Orthogonal Predictive State Recurrent Neural Networks
- In reinforcement learning, all objective functions are not equal
- Interactive Grounded Language Acquisition and Generalization in a 2D World
- Interpretable Counting for Visual Question Answering
- Intriguing Properties of Adversarial Examples
- Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
- Investigating Human Priors for Playing Video Games
- i-RevNet: Deep Invertible Networks
- Isolating Sources of Disentanglement in Variational Autoencoders
- Iterative GANs for Rotating Visual Objects
- Jointly Learning "What" and "How" from Instructions and Goal-States
- Kernel Implicit Variational Inference
- Kronecker-factored Curvature Approximations for Recurrent Neural Networks
- Kronecker Recurrent Units
- Large scale distributed neural network training through online distillation
- Large Scale Optimal Transport and Mapping Estimation
- Latent Constraints: Learning to Generate Conditionally from Unconditional Generative Models
- Latent Space Oddity: on the Curvature of Deep Generative Models
- Learning a Generative Model for Validity in Complex Discrete Structures
- LEARNING AND ANALYZING VECTOR ENCODING OF SYMBOLIC REPRESENTATION
- Learning and Memorization
- Learning an Embedding Space for Transferable Robot Skills
- Learning a neural response metric for retinal prosthesis
- Learning Approximate Inference Networks for Structured Prediction
- Learning Awareness Models
- Learning Causal Mechanisms
- Learning Deep Mean Field Games for Modeling Large Population Behavior
- Learning Deep Models: Critical Points and Local Openness
- Learning Differentially Private Recurrent Language Models
- Learning Discrete Weights Using the Local Reparameterization Trick
- Learning Disentangled Representations with Wasserstein Auto-Encoders
- Learning Efficient Tensor Representations with Ring Structure Networks
- Learning from Between-class Examples for Deep Sound Recognition
- Learning From Noisy Singly-labeled Data
- Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning
- Learning How Not to Act in Text-based Games
- Learning how to explain neural networks: PatternNet and PatternAttribution
- Learning Intrinsic Sparse Structures within Long Short-Term Memory
- Learning Invariances for Policy Generalization
- Learning Invariance with Compact Transforms
- Learning Latent Permutations with Gumbel-Sinkhorn Networks
- Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization
- Learning Longer-term Dependencies in RNNs with Auxiliary Losses
- Learning One-hidden-layer Neural Networks with Landscape Design
- Learning Parametric Closed-Loop Policies for Markov Potential Games
- Learning Representations and Generative Models for 3D Point Clouds
- Learning Rich Image Representation with Deep Layer Aggregation
- Learning Robust Rewards with Adverserial Inverse Reinforcement Learning
- Learning Sparse Latent Representations with the Deep Copula Information Bottleneck
- Learning Sparse Neural Networks through L_0 Regularization
- Learning to cluster in order to transfer across domains and tasks
- Learning to Count Objects in Natural Images for Visual Question Answering
- Learning to Infer
- Learning to Learn Without Labels
- Learning to Multi-Task by Active Sampling
- Learning to Organize Knowledge with N-Gram Machines
- Learning to Represent Programs with Graphs
- LEARNING TO SHARE: SIMULTANEOUS PARAMETER TYING AND SPARSIFICATION IN DEEP LEARNING
- Learning to Teach
- Learning via social awareness: improving sketch representations with facial feedback
- Learning Wasserstein Embeddings
- Learn to Pay Attention
- Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
- Leveraging Constraint Logic Programming for Neural Guided Program Synthesis
- Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
- Lifelong Learning with Dynamically Expandable Networks
- Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values
- Loss-aware Weight Quantization of Deep Networks
- LSH-SAMPLING BREAKS THE COMPUTATIONAL CHICKEN-AND-EGG LOOP IN ADAPTIVE STOCHASTIC GRADIENT ESTIMATION
- LSTM Iteration Networks: An Exploration of Differentiable Path Finding
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
- MaskGAN: Better Text Generation via Filling in the _______
- Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent
- Matrix capsules with EM routing
- Maximum a Posteriori Policy Optimisation
- Measuring the Intrinsic Dimension of Objective Landscapes
- MemCNN: a Framework for Developing Memory Efficient Deep Invertible Networks
- Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks
- Memory Architectures in Recurrent Neural Network Language Models
- Memory Augmented Control Networks
- Memory-based Parameter Adaptation
- Meta-Learning a Dynamical Language Model
- Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
- Meta-Learning for Batch Mode Active Learning
- Meta-Learning for Semi-Supervised Few-Shot Classification
- META LEARNING SHARED HIERARCHIES
- MGAN: Training Generative Adversarial Nets with Multiple Generators
- Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation
- Minimally Redundant Laplacian Eigenmaps
- Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled Diversity
- Mitigating Adversarial Effects Through Randomization
- Mixed Precision Training
- Mixed Precision Training of Convolutional Neural Networks using Integer Operations
- mixup: Beyond Empirical Risk Minimization
- Model compression via distillation and quantization
- Model-Ensemble Trust-Region Policy Optimization
- Modular Continual Learning in a Unified Visual Environment
- Monotonic Chunkwise Attention
- Monotonic models for real-time dynamic malware detection
- Multi-Agent Generative Adversarial Imitation Learning
- Multi-level Residual Networks from Dynamical Systems View
- Multi-Mention Learning for Reading Comprehension with Neural Cascades
- Multiple Source Domain Adaptation with Adversarial Learning
- Multi-Scale Dense Networks for Resource Efficient Image Classification
- Multi-Task Learning for Document Ranking and Query Suggestion
- Multi-View Data Generation Without View Supervision
- N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning
- NAM - Unsupervised Cross-Domain Image Mapping without Cycles or GANs
- Natural Language Inference over Interaction Space
- Negative eigenvalues of the Hessian in deep neural networks
- NerveNet: Learning Structured Policy with Graph Neural Networks
- Neumann Optimizer: A Practical Optimization Algorithm for Deep Neural Networks
- Neural-Guided Deductive Search for Real-Time Program Synthesis from Examples
- Neural Language Modeling by Jointly Learning Syntax and Lexicon
- Neural Map: Structured Memory for Deep Reinforcement Learning
- Neural network parameter regression for lattice quantum chromodynamics simulations in nuclear and particle physics
- Neural Program Search: Solving Programming Tasks from Description and Examples
- Neural Sketch Learning for Conditional Program Generation
- Neural Speed Reading via Skim-RNN
- Neuron as an Agent
- Noisy Networks For Exploration
- Non-Autoregressive Neural Machine Translation
- Nonlinear Acceleration of CNNs
- No Spurious Local Minima in a Two Hidden Unit ReLU Network
- Not-So-Random Features
- One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
- Online Learning Rate Adaptation with Hypergradient Descent
- Online variance-reducing optimization
- On the Convergence of Adam and Beyond
- On the Discrimination-Generalization Tradeoff in GANs
- On the Expressive Power of Overlapping Architectures of Deep Learning
- On the importance of single directions for generalization
- On the Information Bottleneck Theory of Deep Learning
- On the insufficiency of existing momentum schemes for Stochastic Optimization
- On the Limitation of Local Intrinsic Dimensionality for Characterizing the Subspaces of Adversarial Examples
- On the regularization of Wasserstein GANs
- On the State of the Art of Evaluation in Neural Language Models
- On Unifying Deep Generative Models
- Overcoming Catastrophic Interference using Conceptor-Aided Backpropagation
- Parallelizing Linear Recurrent Neural Nets Over Sequence Length
- Parameter Space Noise for Exploration
- Parametric Adversarial Divergences are Good Task Losses for Generative Modeling
- Parametrized Hierarchical Procedures for Neural Programming
- PDE-Net: Learning PDEs from Data
- Pelee: A Real-Time Object Detection System on Mobile Devices
- PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
- PixelNN: Example-based Image Synthesis
- PixelSNAIL: An Improved Autoregressive Generative Model
- Polar Transformer Networks
- Policy Optimization by Genetic Distillation
- Policy Optimization with Second-Order Advantage Information
- PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures
- Practical Hyperparameter Optimization
- Predicting Embryo Morphokinetics in Videos with Late Fusion Nets & Dynamic Decoders
- Predicting Floor-Level for 911 Calls with Neural Networks and Smartphone Sensor Data
- Predict Responsibly: Increasing Fairness by Learning to Defer
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
- Proximal Backpropagation
- Quantitatively Evaluating GANs With Divergences Proposed for Training
- Realistic Evaluation of Semi-Supervised Learning Algorithms
- Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
- Reconstructing evolutionary trajectories of mutations in cancer
- Regret Minimization for Partially Observable Deep Reinforcement Learning
- Regularization Neural Networks via Constrained Virtual Movement Field
- Regularizing and Optimizing LSTM Language Models
- Reinforcement Learning Algorithm Selection
- Reinforcement Learning from Imperfect Demonstrations
- Reinforcement Learning on Web Interfaces using Workflow-Guided Exploration
- ReinforceWalk: Learning to Walk in Graph with Monte Carlo Tree Search
- Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
- Reproducibility, Reusability, and Robustness in Deep Reinforcement Learning
- Residual Connections Encourage Iterative Inference
- RESIDUAL LOSS PREDICTION: REINFORCEMENT LEARNING WITH NO INCREMENTAL FEEDBACK
- Resilient Backpropagation (Rprop) for Batch-learning in TensorFlow
- Rethinking Style and Content Disentanglement in Variational Autoencoders
- Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
- Reward Estimation for Variance Reduction in Deep Reinforcement Learning
- Robustness of Classifiers to Universal Perturbations: A Geometric Perspective
- Rotational Unit of Memory
- Routing Networks: Adaptive Selection of Non-Linear Functions for Multi-Task Learning
- Scalable Estimation via LSH Samplers (LSS)
- Scalable Private Learning with PATE
- SCAN: Learning Hierarchical Compositional Visual Concepts
- Searching for Activation Functions
- SEARNN: Training RNNs with global-local losses
- Selecting the Best in GANs Family: a Post Selection Inference Framework
- Self-ensembling for visual domain adaptation
- Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
- Semantic Interpolation in Implicit Models
- Semiparametric Reinforcement Learning
- Semi-parametric topological memory for navigation
- Semi-Supervised Few-Shot Learning with MAML
- Semi-Supervised Learning With GANs: Revisiting Manifold Regularization
- Sensitivity and Generalization in Neural Networks: an Empirical Study
- SGD Learns Over-parameterized Networks that Provably Generalize on Linearly Separable Data
- SGD on Random Mixtures: Private Machine Learning under Data Breach Threats
- ShakeDrop regularization
- Shifting Mean Activation Towards Zero with Bipolar Activation Functions
- Simple and efficient architecture search for Convolutional Neural Networks
- Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings
- Simulating Action Dynamics with Neural Process Networks
- Skip Connections Eliminate Singularities
- Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
- SMASH: One-Shot Model Architecture Search through HyperNetworks
- Smooth Loss Functions for Deep Top-k Classification
- Sobolev GAN
- Sparse Persistent RNNs: Squeezing Large Recurrent Networks On-Chip
- Spatially Parallel Convolutions
- Spatially Transformed Adversarial Examples
- Spectral Capsule Networks
- SpectralNet: Spectral Clustering using Deep Neural Networks
- Spectral Normalization for Generative Adversarial Networks
- SpectralWords: Spectral Embeddings Approach to Word Similarity Task for Large Vocabularies
- Spherical CNNs
- Stabilizing Adversarial Nets with Prediction Methods
- Stable and Effective Trainable Greedy Decoding for Sequence to Sequence Learning
- Stable Distribution Alignment Using the Dual of the Adversarial Distance
- Stacked Filters Stationary Flow For Hardware-Oriented Acceleration Of Deep Convolutional Neural Networks
- Stochastic Activation Pruning for Robust Adversarial Defense
- Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks
- STOCHASTIC GRADIENT LANGEVIN DYNAMICS THAT EXPLOIT NEURAL NETWORK STRUCTURE
- Stochastic Variational Video Prediction
- SufiSent - Universal Sentence Representations Using Suffix Encodings
- Syntax-Directed Variational Autoencoder for Structured Data
- Synthesizing Audio with GANs
- Synthesizing realistic neural population activity patterns using Generative Adversarial Networks
- Synthetic and Natural Noise Both Break Neural Machine Translation
- Systematic Weight Pruning of DNNs using Alternating Direction Method of Multipliers
- TD or not TD: Analyzing the Role of Temporal Differencing in Deep Reinforcement Learning
- Tempered Adversarial Networks
- Temporal Difference Models: Model-Free Deep RL for Model-Based Control
- Temporally Efficient Deep Learning with Spikes
- THE EFFECTIVENESS OF A TWO-LAYER NEURAL NETWORK FOR RECOMMENDATIONS
- The High-Dimensional Geometry of Binary Neural Networks
- The Implicit Bias of Gradient Descent on Separable Data
- The Kanerva Machine: A Generative Distributed Memory
- The loss surface and expressivity of deep convolutional neural networks
- The Mirage of Action-Dependent Baselines in Reinforcement Learning
- The power of deeper networks for expressing natural functions
- The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
- Thermometer Encoding: One Hot Way To Resist Adversarial Examples
- The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings
- Time-Dependent Representation for Neural Event Sequence Prediction
- To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression
- Towards better understanding of gradient-based attribution methods for Deep Neural Networks
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Towards Image Understanding from Deep Compression Without Decoding
- Towards Mixed-initiative generation of multi-channel sequential structure
- Towards Neural Phrase-based Machine Translation
- Towards Provable Control for Unknown Linear Dynamical Systems
- Towards Reverse-Engineering Black-Box Neural Networks
- Towards Specification-Directed Program Repair
- Towards Synthesizing Complex Programs From Input-Output Examples
- Towards Variational Generation of Small Graphs
- Training and Inference with Integers in Deep Neural Networks
- Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples
- Training GANs with Optimism
- TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GAN
- Training Shallow and Thin Networks for Acceleration via Knowledge Distillation with Conditional Adversarial Networks
- Training wide residual networks for deployment using a single bit for each weight
- TransNets for Review Generation
- TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
- Tree-to-tree Neural Networks for Program Translation
- TRUNCATED HORIZON POLICY SEARCH: COMBINING REINFORCEMENT LEARNING & IMITATION LEARNING
- Trust-PCL: An Off-Policy Trust Region Method for Continuous Control
- Twin Networks: Matching the Future for Sequence Generation
- Unbiased Online Recurrent Optimization
- Uncertainty Estimation via Stochastic Batch Normalization
- Understanding Deep Neural Networks with Rectified Linear Units
- Understanding image motion with group representations
- Understanding Short-Horizon Bias in Stochastic Meta-Optimization
- Understanding the Loss Surface of Single-Layered Neural Networks for Binary Classification
- Universal Agent for Disentangling Environments and Tasks
- Universal Successor Representations for Transfer Reinforcement Learning
- Unsupervised Cipher Cracking Using Discrete GANs
- Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration
- Unsupervised Machine Translation Using Monolingual Corpora Only
- Unsupervised Neural Machine Translation
- Unsupervised Representation Learning by Predicting Image Rotations
- Variance-based Gradient Compression for Efficient Distributed Deep Learning
- Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines
- Variational Continual Learning
- Variational image compression with a scale hyperprior
- Variational Inference of Disentangled Latent Concepts from Unlabeled Observations
- Variational Message Passing with Structured Inference Networks
- Variational Network Quantization
- Visual Learning With Unlabeled Video and Look-Around Policies
- Viterbi-based Pruning for Sparse Matrix with Fixed and High Index Compression Ratio
- VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop
- Wasserstein Auto-Encoders
- Wasserstein Auto-Encoders: Latent Dimensionality and Random Encoders
- Wavelet Pooling for Convolutional Neural Networks
- Weighted Geodesic Distance Following Fermat's Principle
- Weightless: Lossy weight encoding for deep neural network compression
- WHAI: Weibull Hybrid Autoencoding Inference for Deep Topic Modeling
- What Can Machine Learning Do? Workforce Implications
- When is a Convolutional Filter Easy to Learn?
- Winner's Curse? On Pace, Progress, and Empirical Rigor
- Word translation without parallel data
- WRPN: Wide Reduced-Precision Networks
- Zero-Shot Visual Imitation