ICLR 2017 论文列表
5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings.
|
Hadamard Product for Low-rank Bilinear Pooling.
A Learned Representation For Artistic Style.
HyperNetworks.
Dropout with Expectation-linear Regularization.
Neural Photo Editing with Introspective Adversarial Networks.
Hierarchical Multiscale Recurrent Neural Networks.
Why Deep Neural Networks for Function Approximation?
HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving.
Tighter bounds lead to improved classifiers.
Understanding Trainable Sparse Coding with Matrix Factorization.
An Actor-Critic Algorithm for Sequence Prediction.
Pointer Sentinel Mixture Models.
Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks.
Adversarial Training Methods for Semi-Supervised Text Classification.
Sparsely-Connected Neural Networks: Towards Efficient VLSI Implementation of Deep Neural Networks.
Semi-Supervised Classification with Graph Convolutional Networks.
Efficient Representation of Low-Dimensional Manifolds using Deep Networks.
Inductive Bias of Deep Convolutional Networks through Pooling Geometry.
Recurrent Mixture Density Network for Spatiotemporal Visual Attention.
Predicting Medications from Diagnostic Codes with Recurrent Neural Networks.
Adversarial Machine Learning at Scale.
Learning Recurrent Representations for Hierarchical Behavior Modeling.
Reasoning with Memory Augmented Neural Networks for Language Comprehension.
Learning Invariant Representations Of Planar Curves.
Geometry of Polysemy.
Do Deep Convolutional Nets Really Need to be Deep and Convolutional?
Discrete Variational Autoencoders.
Towards Deep Interpretability (MUS-ROVER II): Learning Hierarchical Representations of Tonal Music.
Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling.
Support Regularized Sparse Coding and Its Fast Encoder.
Batch Policy Gradient Methods for Improving Neural Conversation Models.
Stick-Breaking Variational Autoencoders.
Faster CNNs with Direct Sparse Convolutions and Guided Pruning.
Towards the Limit of Network Quantization.
Adversarial Feature Learning.
Identity Matters in Deep Learning.
Delving into Transferable Adversarial Examples and Black-box Attacks.
Learning to Compose Words into Sentences with Reinforcement Learning.
Training deep neural-networks using a noise adaptation layer.
On Detecting Adversarial Perturbations.
Temporal Ensembling for Semi-Supervised Learning.
Sample Efficient Actor-Critic with Experience Replay.
Deep Multi-task Representation Learning: A Tensor Factorisation Approach.
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys.
Incremental Network Quantization: Towards Lossless CNNs with Low-precision Weights.
Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning.
Energy-based Generative Adversarial Networks.
Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening.
Loss-aware Binarization of Deep Networks.
Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning.
Revisiting Classifier Two-Sample Tests.
FractalNet: Ultra-Deep Neural Networks without Residuals.
Deep Information Propagation.
Learning through Dialogue Interactions by Asking Questions.
Adversarially Learned Inference.
Dialogue Learning With Human-in-the-Loop.
Automatic Rule Extraction from Long Short Term Memory Networks.
The Neural Noisy Channel.
Deep Variational Information Bottleneck.
Variable Computation in Recurrent Neural Networks.
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks.
DeepCoder: Learning to Write Programs.
Learning to Navigate in Complex Environments.
Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU.
Learning a Natural Language Interface with Neural Programmer.
SGDR: Stochastic Gradient Descent with Warm Restarts.
Recurrent Batch Normalization.
Density estimation using Real NVP.
Combining policy gradient and Q-learning.
Paleo: A Performance Model for Deep Neural Networks.
Latent Sequence Decompositions.
Online Bayesian Transfer Learning for Sequential Data Modeling.
Categorical Reparameterization with Gumbel-Softmax.
Visualizing Deep Neural Network Decisions: Prediction Difference Analysis.
Offline bilingual word vectors, orthogonal transformations and the inverted softmax.
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework.
Mollifying Networks.
Generative Multi-Adversarial Networks.
Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data.
Recurrent Hidden Semi-Markov Model.
Frustratingly Short Attention Spans in Neural Language Modeling.
TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency.
Unrolled Generative Adversarial Networks.
The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables.
Regularizing CNNs with Locally Constrained Decorrelations.
A Structured Self-Attentive Sentence Embedding.
Sigma Delta Quantized Networks.
Trusting SVM for Piecewise Linear CNNs.
Learning to superoptimize programs.
A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks.
Learning Features of Music From Scratch.
Multi-view Recurrent Neural Acoustic Word Embeddings.
Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain.
EPOpt: Learning Robust Neural Network Policies Using Model Ensembles.
Recurrent Environment Simulators.
Quasi-Recurrent Neural Networks.
Lie-Access Neural Turing Machines.
Hyperband: Bandit-Based Configuration Evaluation for Hyperparameter Optimization.
Introspection: Accelerating Neural Network Training By Learning Weight Evolution.
Tree-structured decoding with doubly-recurrent neural networks.
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer.
A recurrent neural network without chaos.
Variational Lossy Autoencoder.
LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation.
Deep Probabilistic Programming.
Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations.
Structured Attention Networks.
Lossy Image Compression with Compressive Autoencoders.
Exploring Sparsity in Recurrent Neural Networks.
Metacontrol for Adaptive Imagination-Based Optimization.
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model.
Dynamic Coattention Networks For Question Answering.
Incorporating long-range consistency in CNN-based texture generation.
Bidirectional Attention Flow for Machine Comprehension.
DeepDSL: A Compilation-based Domain-Specific Language for Deep Learning.
Machine Comprehension Using Match-LSTM and Answer Pointer.
Designing Neural Network Architectures using Reinforcement Learning.
Query-Reduction Networks for Question Answering.
Pruning Convolutional Neural Networks for Resource Efficient Inference.
Calibrating Energy-based Generative Adversarial Networks.
Deep Learning with Dynamic Computation Graphs.
Improving Policy Gradient by Exploring Under-appreciated Rewards.
Learning to Perform Physics Experiments via Deep Reinforcement Learning.
Capacity and Trainability in Recurrent Neural Networks.
A Simple but Tough-to-Beat Baseline for Sentence Embeddings.
Words or Characters? Fine-grained Gating for Reading Comprehension.
Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks.
Learning to Remember Rare Events.
A Compositional Object-Based Approach to Learning Physical Dynamics.
DSD: Dense-Sparse-Dense Training for Deep Neural Networks.
Trained Ternary Quantization.
On the Quantitative Analysis of Decoder-Based Generative Models.
Optimal Binary Autoencoding with Pairwise Correlations.
Autoencoding Variational Inference For Topic Models.
Training Compressed Fully-Connected Networks with a Density-Diversity Penalty.
Data Noising as Smoothing in Neural Network Language Models.
A Compare-Aggregate Model for Matching Text Sequences.
Learning to Optimize.
Learning Curve Prediction with Bayesian Neural Networks.
Generalizing Skills with Semi-Supervised Reinforcement Learning.
Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy.
Towards a Neural Statistician.
Decomposing Motion and Content for Natural Video Sequence Prediction.
Neuro-Symbolic Program Synthesis.
Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning.
Snapshot Ensembles: Train 1, Get M for Free.
PixelVAE: A Latent Variable Model for Natural Images.
Deep Biaffine Attention for Neural Dependency Parsing.
Diet Networks: Thin Parameters for Fat Genomics.
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning.
Learning to Query, Reason, and Answer Questions On Ambiguous Texts.
Steerable CNNs.
Tracking the World State with Recurrent Entity Networks.
Neural Program Lattices.
Soft Weight-Sharing for Neural Network Compression.
Episodic Exploration for Deep Deterministic Policies for StarCraft Micromanagement.
Program Synthesis for Character Level Language Modeling.
Variational Recurrent Adversarial Deep Domain Adaptation.
Third Person Imitation Learning.
Unsupervised Cross-Domain Image Generation.
Improving Neural Language Models with a Continuous Cache.
Highway and Residual Networks learn Unrolled Iterative Estimation.
Mode Regularized Generative Adversarial Networks.
PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications.
An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax.
Emergence of foveal image sampling from learning to attend in visual scenes.
What does it take to generate natural textures?
Transfer of View-manifold Learning to Similarity Perception of Novel Objects.
Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning.
Efficient Vector Representation for Documents through Corruption.
Improving Generative Adversarial Networks with Denoising Feature Matching.
Multilayer Recurrent Network Models of Primate Retinal Ganglion Cell Responses.
Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes.
Filter shaping for Convolutional Neural Networks.
Learning to Generate Samples from Noise through Infusion Training.
Pruning Filters for Efficient ConvNets.
Distributed Second-Order Optimization using Kronecker-Factored Approximations.
Nonparametric Neural Networks.
Stochastic Neural Networks for Hierarchical Reinforcement Learning.
Learning Visual Servoing with Deep Features and Fitted Q-Iteration.
Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer.
Topology and Geometry of Half-Rectified Network Optimization.
Maximum Entropy Flow Networks.
Learning Graphical State Transitions.
Amortised MAP Inference for Image Super-resolution.
Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data.
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima.
Learning to Act by Predicting the Future.
Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic.
Neural Architecture Search with Reinforcement Learning.
Understanding deep learning requires rethinking generalization.
Multi-Agent Cooperation and the Emergence of (Natural) Language.
Reinforcement Learning with Unsupervised Auxiliary Tasks.
Towards Principled Methods for Training Generative Adversarial Networks.
Learning End-to-End Goal-Oriented Dialog.
Optimization as a Model for Few-Shot Learning.
End-to-end Optimized Image Compression.
Making Neural Programming Architectures Generalize via Recursion.
