Filter Results:
- Full text PDF available (29)
Publication Year
2000
2018
- This year (8)
- Last 5 years (38)
- Last 10 years (45)
Publication Type
Co-author
Journals and Conferences
Learn More
- Christian Szegedy, Wojciech Zaremba, +4 authors Rob Fergus
- ICLR
- 2014
Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks. While their expressiveness is the reason they… (More)
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. We focus on two applications of GANs: semi-supervised… (More)
- Wojciech Zaremba, Ilya Sutskever, Oriol Vinyals
- ArXiv
- 2014
We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units. Dropout, the most successful technique for regularizing neural networks,… (More)
Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous words and some… (More)
- Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann LeCun
- ArXiv
- 2013
Convolutional Neural Networks are extremely efficient architectures in image and audio recognition tasks, thanks to their ability to exploit the local translational invariance of signal classes over… (More)
- Emily L. Denton, Wojciech Zaremba, Joan Bruna, Yann LeCun, Rob Fergus
- NIPS
- 2014
We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy, but each image… (More)
Neural Machine Translation (NMT) has recently attracted a l ot of attention due to the very high performance achieved by deep neural network s in other domains. An inherent weakness in existing NMT… (More)
- Rafal Józefowicz, Wojciech Zaremba, Ilya Sutskever
- ICML
- 2015
The Recurrent Neural Network (RNN) is an extremely powerful sequence model that is often difficult to train. The Long Short-Term Memory (LSTM) is a specific RNN architecture whose design makes it… (More)
- Greg Brockman, Vicki Cheung, +4 authors Wojciech Zaremba
- ArXiv
- 2016
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 results… (More)
- Marcin Andrychowicz, Filip Wolski, +7 authors Wojciech Zaremba
- NIPS
- 2017
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-efficient learning… (More)