• Publications
  • Influence
Intriguing properties of neural networks
TLDR
We find that deep neural networks learn input-output mappings that are fairly discontinuous to a significant extend. Expand
  • 5,481
  • 717
  • PDF
Improved Techniques for Training GANs
TLDR
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. Expand
  • 3,734
  • 579
  • PDF
Recurrent Neural Network Regularization
TLDR
We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units, and show that it substantially reduces overfitting on a variety of tasks. Expand
  • 1,550
  • 241
  • PDF
Spectral Networks and Locally Connected Networks on Graphs
TLDR
We show through experiments that for low-dimensional graphs it is possible to learn convolutional layers with a number of parameters independent of the input size, resulting in efficient deep architectures. Expand
  • 1,675
  • 187
  • PDF
OpenAI Gym
OpenAI Gym1 is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can share their resultsExpand
  • 1,385
  • 184
  • PDF
Hindsight Experience Replay
TLDR
We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering. Expand
  • 642
  • 147
  • PDF
Sequence Level Training with Recurrent Neural Networks
TLDR
We propose a novel sequence level training algorithm that directly optimizes the metric used at test time, such as BLEU or ROUGE. Expand
  • 878
  • 130
  • PDF
An Empirical Exploration of Recurrent Network Architectures
TLDR
We evaluated over ten thousand different RNN architectures, and identified an architecture that outperforms both the LSTM and the recently-introduced Gated Recurrent Unit on some but not all tasks. Expand
  • 1,112
  • 88
  • PDF
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
TLDR
We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. Expand
  • 967
  • 86
  • PDF
Addressing the Rare Word Problem in Neural Machine Translation
TLDR
Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. Expand
  • 578
  • 79
  • PDF