Mixed Precision Training
Comments Published as a conference paper at ICLR 2018
期刊&会议
ICLR
International Conference on Learning Representations · 会议 · Machine Learning
Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm
Comments ICLR 2018
A Bayesian Perspective on Generalization and Stochastic Gradient Descent
Comments 13 pages, 9 figures. Published as a conference paper at ICLR 2018
Towards Reverse-Engineering Black-Box Neural Networks
Comments 20 pages, 12 figures, to appear at ICLR'18. Code: https://goo.gl/MbYfsv
Neural Program Search: Solving Programming Tasks from Description and Examples
Comments 9 pages, 3 figures, ICLR workshop
Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering
Comments 14 pages (main paper: 10 pages). Published as a conference paper at ICLR 2018
Boosting Dilated Convolutional Networks with Mixed Tensor Decompositions
Comments Published as a conference paper at ICLR 2018
Critical Percolation as a Framework to Analyze the Training of Deep Networks
Comments Accepted to ICLR 2018 as a conference paper
Learning Intrinsic Sparse Structures within Long Short-Term Memory
Comments Published in ICLR 2018 ( the Sixth International Conference on Learning Representations)
Natural Language Inference over Interaction Space: ICLR 2018 Reproducibility Report
Comments as part of ICLR 2018 Reproducibility Challenge
Learning Latent Representations in Neural Networks for Clustering through Pseudo Supervision and Graph-based Activity Regularization
Comments To appear in proceedings of the International Conference on Learning Representations 2018
Improving the Universality and Learnability of Neural Programmer-Interpreters with Combinator Abstraction
Comments Published as a conference paper at ICLR 2018
Expressive power of recurrent neural networks
Comments Accepted as a conference paper at ICLR 2018
Byte-Level Recursive Convolutional Auto-Encoder for Text
Comments Rejected from ICLR 2018
Training Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN
Comments Accepted by Sixth International Conference on Learning Representations (ICLR 2018). Xu Chen and Jiang Wang contributed equally
Trace norm regularization and faster inference for embedded speech recognition RNNs
Comments Our optimized inference kernels are available at: https://github.com/PaddlePaddle/farm (Note: This paper was submitted to, but rejected from, ICLR 2018. We believe it may still be of value to others. Please see the discussion here: https://openreview.net/forum?id=B1tC-LT6W)
Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers
Comments accepted to ICLR 2018, 11 pages
FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension
Comments Published in Sixth International Conference on Learning Representations (ICLR), 2018
Graph Attention Networks
Comments To appear at ICLR 2018. 12 pages, 2 figures
Skip RNN: Learning to Skip State Updates in Recurrent Neural Networks
Comments Accepted as conference paper at ICLR 2018
Multi-level Residual Networks from Dynamical Systems View
Comments Published as a conference paper at ICLR 2018
Learning Discrete Weights Using the Local Reparameterization Trick
Comments ICLR 2018
Alternating Multi-bit Quantization for Recurrent Neural Networks
Comments Published as a conference paper at ICLR 2018
Polar Transformer Networks
Comments Accepted as a conference paper at ICLR 2018
Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
Comments Accepted by Sixth International Conference on Learning Representations (ICLR 2018). Tsui-Wei Weng and Huan Zhang contributed equally
FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
Comments ICLR 2018
Generating Wikipedia by Summarizing Long Sequences
Comments Published as a conference paper at ICLR 2018
Attacking Binarized Neural Networks
Comments Published as a conference paper at ICLR 2018
Stable Distribution Alignment Using the Dual of the Adversarial Distance
Comments ICLR 2018 Conference Invite to Workshop
Parameter Space Noise for Exploration
Comments Updated to camera-ready ICLR submission
