A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples
Comments 38 pages , ICLR 2017 Workshop Track
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Gated Graph Sequence Neural Networks
Comments Published as a conference paper in ICLR 2016. Fixed a typo
Words or Characters? Fine-grained Gating for Reading Comprehension
Comments Accepted as a conference paper at ICLR 2017
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights
Comments Published by ICLR 2017, and the code is available at https://github.com/Zhouaojun/Incremental-Network-Quantization
Reinterpreting Importance-Weighted Autoencoders
Comments ICLR 2017 Workshop
Audio Super Resolution using Neural Networks
Comments Presented at the 5th International Conference on Learning Representations (ICLR) 2017, Workshop Track, Toulon, France
LR-GAN: Layered Recursive Generative Adversarial Networks for Image Generation
Comments 21 pages, 22 figures, published as a conference paper at ICLR 2017, code available on GitHub
Learning Visual Servoing with Deep Features and Fitted Q-Iteration
Comments ICLR 2017
Efficient Vector Representation for Documents through Corruption
Comments 5th International Conference on Learning Representations, 2017
Sample Efficient Actor-Critic with Experience Replay
Comments 20 pages. Prepared for ICLR 2017
Learning to superoptimize programs
Comments Accepted to ICLR 2017
Coupling Distributed and Symbolic Execution for Natural Language Queries
Comments Accepted by ICML-17; also presented at ICLR-17 Workshop
Getting deep recommenders fit: Bloom embeddings for sparse binary input/output networks
Comments Accepted for publication at ACM RecSys 2017; previous version submitted to ICLR 2016
Input Switched Affine Networks: An RNN Architecture Designed for Interpretability
Comments ICLR 2107 submission: https://openreview.net/forum?id=H1MjAnqxg
Pruning Convolutional Neural Networks for Resource Efficient Inference
Comments 17 pages, 14 figures, ICLR 2017 paper
Topology and Geometry of Half-Rectified Network Optimization
Comments 22 Pages (10 main + Appendices), 4 Figures, 1 Table, Published as a conference paper at ICLR 2017
Understanding Trainable Sparse Coding via Matrix Factorization
Comments Published as a conference paper at ICLR 2017
FractalNet: Ultra-Deep Neural Networks without Residuals
Comments updated with ImageNet results; published as a conference paper at ICLR 2017; project page at http://people.cs.uchicago.edu/~larsson/fractalnet/
RandomOut: Using a convolutional gradient norm to rescue convolutional filters
Comments Extended version of the ICLR 2016 workshop track paper
Delving into adversarial attacks on deep policies
Comments ICLR 2017 Workshop
Tracking the World State with Recurrent Entity Networks
Journal ref ICLR 2017
Here's My Point: Joint Pointer Architecture for Argument Mining
Comments 10 pages; under review for ICLR
SGDR: Stochastic Gradient Descent with Warm Restarts
Comments ICLR 2017 conference paper
Forced to Learn: Discovering Disentangled Representations Without Exhaustive Labels
Comments Abstract accepted at ICLR 2017 Workshop: https://openreview.net/pdf?id=SkCmfeSFg
Maximum Entropy Flow Networks
Comments Accepted at ICLR 2017
Efficient variational Bayesian neural network ensembles for outlier detection
Comments Presented at Workshop track - ICLR 2017
Discrete Variational Autoencoders
Comments Published as a conference paper at ICLR 2017
Making Neural Programming Architectures Generalize via Recursion
Comments Published in ICLR 2017
Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
Comments ICLR '17
Fast Generation for Convolutional Autoregressive Models
Comments Accepted at ICLR 2017 Workshop
