• Publications
  • Influence
Intriguing properties of neural networks
TLDR
It is found that there is no distinction between individual highlevel units and random linear combinations of high level units, according to various methods of unit analysis, and it is suggested that it is the space, rather than the individual units, that contains of the semantic information in the high layers of neural networks.
Improved Techniques for Training GANs
TLDR
This work focuses on two applications of GANs: semi-supervised learning, and the generation of images that humans find visually realistic, and presents ImageNet samples with unprecedented resolution and shows that the methods enable the model to learn recognizable features of ImageNet classes.
OpenAI Gym
TLDR
This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software.
Recurrent Neural Network Regularization
TLDR
This paper shows how to correctly apply dropout to LSTMs, and shows that it substantially reduces overfitting on a variety of tasks.
Spectral Networks and Locally Connected Networks on Graphs
TLDR
This paper considers possible generalizations of CNNs to signals defined on more general domains without the action of a translation group, and proposes two constructions, one based upon a hierarchical clustering of the domain, and another based on the spectrum of the graph Laplacian.
Hindsight Experience Replay
TLDR
A novel technique is presented which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering and may be seen as a form of implicit curriculum.
Sequence Level Training with Recurrent Neural Networks
TLDR
This work proposes a novel sequence level training algorithm that directly optimizes the metric used at test time, such as BLEU or ROUGE, and outperforms several strong baselines for greedy generation.
Domain randomization for transferring deep neural networks from simulation to the real world
TLDR
This paper explores domain randomization, a simple technique for training models on simulated images that transfer to real images by randomizing rendering in the simulator, and achieves the first successful transfer of a deep neural network trained only on simulated RGB images to the real world for the purpose of robotic control.
An Empirical Exploration of Recurrent Network Architectures
TLDR
It is found that adding a bias of 1 to the LSTM's forget gate closes the gap between the L STM and the recently-introduced Gated Recurrent Unit (GRU) on some but not all tasks.
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
TLDR
Using large state-of-the-art models, this work demonstrates speedups of convolutional layers on both CPU and GPU by a factor of 2 x, while keeping the accuracy within 1% of the original model.
...
...