International Conference on Learning Representations (ICLR) - 2017

Conference Proceedings:

Key: PC - Pseudocode, OSC - Open Source Code, OSD - Open Datasets, DS - Dataset Splits, HS - Hardware Specification, SD - Software Dependencies, ES - Experiment Setup

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks 5
A Compare-Aggregate Model for Matching Text Sequences 4
A Compositional Object-Based Approach to Learning Physical Dynamics 2
A Differentiable Physics Engine for Deep Learning in Robotics 2
A Learned Representation For Artistic Style 3
A STRUCTURED SELF-ATTENTIVE SENTENCE EMBEDDING 3
A Simple but Tough-to-Beat Baseline for Sentence Embeddings 5
A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Samples 2
A recurrent neural network without chaos 3
Adaptive Feature Abstraction for Translating Video to Language 2
Adversarial Feature Learning 3
Adversarial Machine Learning at Scale 4
Adversarial Training Methods for Semi-Supervised Text Classification 4
Adversarial examples in the physical world 3
Adversarially Learned Inference 6
Amortised MAP Inference for Image Super-resolution 3
An Actor-Critic Algorithm for Sequence Prediction 6
An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax 5
Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain 2
Autoencoding Variational Inference For Topic Models 4
Automated Generation of Multilingual Clusters for the Evaluation of Distributed Representations 1
Automatic Rule Extraction from Long Short Term Memory Networks 3
Batch Policy Gradient Methods for Improving Neural Conversation Models 3
Bidirectional Attention Flow for Machine Comprehension 5
Bit-Pragmatic Deep Neural Network Computing 2
Calibrating Energy-based Generative Adversarial Networks 3
Capacity and Trainability in Recurrent Neural Networks 3
Categorical Reparameterization with Gumbel-Softmax 3
Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning 3
Charged Point Normalization: An Efficient Solution to the Saddle Point Problem 3
Combining policy gradient and Q-learning 2
Compositional Kernel Machines 3
DSD: Dense-Sparse-Dense Training for Deep Neural Networks 5
Data Noising as Smoothing in Neural Network Language Models 5
Dataset Augmentation in Feature Space 3
Decomposing Motion and Content for Natural Video Sequence Prediction 3
Deep Biaffine Attention for Neural Dependency Parsing 3
Deep Information Propagation 2
Deep Learning with Dynamic Computation Graphs 5
Deep Learning with Sets and Point Clouds 3
Deep Multi-task Representation Learning: A Tensor Factorisation Approach 4
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning 5
Deep Probabilistic Programming 5
Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data 4
Deep Variational Information Bottleneck 3
DeepCoder: Learning to Write Programs 1
DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning 5
Delving into Transferable Adversarial Examples and Black-box Attacks 2
Density estimation using Real NVP 3
Designing Neural Network Architectures using Reinforcement Learning 5
Development of JavaScript-based deep learning platform and application to distributed training 6
Dialogue Learning With Human-in-the-Loop 4
Diet Networks: Thin Parameters for Fat Genomics 5
Discovering objects and their relations from entangled scene representations 1
Discrete Variational Autoencoders 2
Distributed Second-Order Optimization using Kronecker-Factored Approximations 3
Do Deep Convolutional Nets Really Need to be Deep and Convolutional? 3
Dropout with Expectation-linear Regularization 3
Dynamic Coattention Networks For Question Answering 3
EPOpt: Learning Robust Neural Network Policies Using Model Ensembles 4
Efficient Representation of Low-Dimensional Manifolds using Deep Networks 0
Efficient Softmax Approximation for GPUs 3
Efficient Vector Representation for Documents through Corruption 5
Emergence of foveal image sampling from learning to attend in visual scenes 3
End-to-end Optimized Image Compression 2
Energy-based Generative Adversarial Networks 2
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys 4
Episodic Exploration for Deep Deterministic Policies for StarCraft Micromanagement 2
Exploring Sparsity in Recurrent Neural Networks 5
Exponential Machines 6
Extrapolation and learning equations 3
FILTER SHAPING FOR CONVOLUTIONAL NEURAL NETWORKS 3
Fast Chirplet Transform to Enhance CNN Machine Listening - Validation on Animal calls and Speech 5
Faster CNNs with Direct Sparse Convolutions and Guided Pruning 6
Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks 3
FractalNet: Ultra-Deep Neural Networks without Residuals 3
Frustratingly Short Attention Spans in Neural Language Modeling 3
Gated Multimodal Units for Information Fusion 5
Generalizable Features From Unsupervised Learning 2
Generalizing Skills with Semi-Supervised Reinforcement Learning 3
Generating Interpretable Images with Controllable Structure 3
Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy 4
Generative Multi-Adversarial Networks 4
Geometry of Polysemy 3
Hadamard Product for Low-rank Bilinear Pooling 4
Hierarchical Multiscale Recurrent Neural Networks 3
Highway and Residual Networks learn Unrolled Iterative Estimation 4
HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving 3
HyperNetworks 3
Hyperband: Bandit-Based Configuration Evaluation for Hyperparameter Optimization 5
Identity Matters in Deep Learning 3
Improving Generative Adversarial Networks with Denoising Feature Matching 4
Improving Neural Language Models with a Continuous Cache 3
Improving Policy Gradient by Exploring Under-appreciated Rewards 2
Incorporating long-range consistency in CNN-based texture generation 2
Incremental Network Quantization: Towards Lossless CNNs with Low-precision Weights 4
Inductive Bias of Deep Convolutional Networks through Pooling Geometry 3
Introspection:Accelerating Neural Network Training By Learning Weight Evolution 2
LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation 3
Latent Sequence Decompositions 3
Learning Continuous Semantic Representations of Symbolic Expressions 4
Learning Curve Prediction with Bayesian Neural Networks 3
Learning End-to-End Goal-Oriented Dialog 3
Learning Features of Music From Scratch 2
Learning Graphical State Transitions 4
Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning 1
Learning Invariant Representations Of Planar Curves 3
Learning Recurrent Representations for Hierarchical Behavior Modeling 3
Learning Visual Servoing with Deep Features and Fitted Q-Iteration 5
Learning a Natural Language Interface with Neural Programmer 5
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks 4
Learning in Implicit Generative Models 0
Learning through Dialogue Interactions by Asking Questions 3
Learning to Act by Predicting the Future 1
Learning to Compose Words into Sentences with Reinforcement Learning 3
Learning to Discover Sparse Graphical Models 3
Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learning 4
Learning to Generate Samples from Noise through Infusion Training 3
Learning to Navigate in Complex Environments 2
Learning to Optimize 2
Learning to Perform Physics Experiments via Deep Reinforcement Learning 1
Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening 4
Learning to Query, Reason, and Answer Questions On Ambiguous Texts 2
Learning to Remember Rare Events 4
Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning 3
Learning to superoptimize programs 3
Lie-Access Neural Turing Machines 2
Lifelong Perceptual Programming By Example 4
Loss-aware Binarization of Deep Networks 5
Lossy Image Compression with Compressive Autoencoders 3
Machine Comprehension Using Match-LSTM and Answer Pointer 4
Making Neural Programming Architectures Generalize via Recursion 2
Maximum Entropy Flow Networks 2
Metacontrol for Adaptive Imagination-Based Optimization 3
Mode Regularized Generative Adversarial Networks 3
Modular Multitask Reinforcement Learning with Policy Sketches 3
Modularized Morphing of Neural Networks 4
Mollifying Networks 3
Multi-Agent Cooperation and the Emergence of (Natural) Language 2
Multi-view Recurrent Neural Acoustic Word Embeddings 4
Multilayer Recurrent Network Models of Primate Retinal Ganglion Cell Responses 3
Multiplicative LSTM for sequence modelling 4
Neural Architecture Search with Reinforcement Learning 3
Neural Data Filter for Bootstrapping Stochastic Gradient Descent 5
Neural Functional Programming 2
Neural Photo Editing with Introspective Adversarial Networks 4
Neural Program Lattices 2
Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks 3
Neuro-Symbolic Program Synthesis 2
Nonparametric Neural Networks 4
Nonparametrically Learning Activation Functions in Deep Neural Nets 4
Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes 3
Offline bilingual word vectors, orthogonal transformations and the inverted softmax 2
On Detecting Adversarial Perturbations 3
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima 3
On Robust Concepts and Small Neural Nets 0
On the Quantitative Analysis of Decoder-Based Generative Models 4
Online Bayesian Transfer Learning for Sequential Data Modeling 3
Online Structure Learning for Sum-Product Networks with Gaussian Leaves 6
Optimal Binary Autoencoding with Pairwise Correlations 4
Optimization as a Model for Few-Shot Learning 5
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer 4
Paleo: A Performance Model for Deep Neural Networks 5
Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer 5
Perception Updating Networks: On architectural constraints for interpretable video generative models 4
PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications 3
PixelVAE: A Latent Variable Model for Natural Images 3
Pointer Sentinel Mixture Models 4
Predicting Medications from Diagnostic Codes with Recurrent Neural Networks 2
Program Synthesis for Character Level Language Modeling 4
Programming With a Differentiable Forth Interpreter 1
Pruning Convolutional Neural Networks for Resource Efficient Inference 5
Pruning Filters for Efficient ConvNets 5
Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic 4
Quasi-Recurrent Neural Networks 4
Query-Reduction Networks for Question Answering 5
Reasoning with Memory Augmented Neural Networks for Language Comprehension 4
Recurrent Batch Normalization 3
Recurrent Environment Simulators 3
Recurrent Hidden Semi-Markov Model 5
Recurrent Mixture Density Network for Spatiotemporal Visual Attention 4
Recurrent Normalization Propagation 4
Recursive Regression with Neural Networks: Approximating the HJI PDE Solution 2
Regularizing CNNs with Locally Constrained Decorrelations 5
Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU 5
Reinforcement Learning with Unsupervised Auxiliary Tasks 2
RenderGAN: Generating Realistic Labeled Data 3
Revisiting Classifier Two-Sample Tests 3
SGDR: Stochastic Gradient Descent with Warm Restarts 3
Sample Efficient Actor-Critic with Experience Replay 2
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model 5
Semi-Supervised Classification with Graph Convolutional Networks 6
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data 4
Semi-supervised deep learning by metric embedding 5
Shift Aggregate Extract Networks 5
Short and Deep: Sketching and Neural Networks 3
Sigma Delta Quantized Networks 4
Snapshot Ensembles: Train 1, Get M for Free 5
Soft Weight-Sharing for Neural Network Compression 4
Song From PI: A Musically Plausible Network for Pop Music Generation 2
Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks 4
Steerable CNNs 1
Stick-Breaking Variational Autoencoders 5
Stochastic Neural Networks for Hierarchical Reinforcement Learning 4
Structured Attention Networks 5
Support Regularized Sparse Coding and Its Fast Encoder 4
Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning 4
Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity 0
Temporal Ensembling for Semi-Supervised Learning 4
The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables 3
The Neural Noisy Channel 4
Third Person Imitation Learning 3
Tighter bounds lead to improved classifiers 4
TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency 4
Topology and Geometry of Half-Rectified Network Optimization 4
Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music 3
Towards Principled Methods for Training Generative Adversarial Networks 0
Towards a Neural Statistician 4
Towards an automatic Turing test: Learning to evaluate dialogue responses 4
Towards the Limit of Network Quantization 4
Tracking the World State with Recurrent Entity Networks 4
Trained Ternary Quantization 3
Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning 2
Training Compressed Fully-Connected Networks with a Density-Diversity Penalty 4
Training deep neural-networks using a noise adaptation layer 4
Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks 4
Transfer of View-manifold Learning to Similarity Perception of Novel Objects 3
Tree-structured decoding with doubly-recurrent neural networks 3
Trusting SVM for Piecewise Linear CNNs 6
Tuning Recurrent Neural Networks with Reinforcement Learning 2
Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling 3
Understanding Trainable Sparse Coding with Matrix Factorization 3
Understanding deep learning requires rethinking generalization 3
Unrolled Generative Adversarial Networks 3
Unsupervised Cross-Domain Image Generation 2
Unsupervised Perceptual Rewards for Imitation Learning 3
Variable Computation in Recurrent Neural Networks 3
Variational Lossy Autoencoder 3
Variational Recurrent Adversarial Deep Domain Adaptation 3
Visualizing Deep Neural Network Decisions: Prediction Difference Analysis 5
What does it take to generate natural textures? 2
Why Deep Neural Networks for Function Approximation? 0
Words or Characters? Fine-grained Gating for Reading Comprehension 4
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations 3
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework 2