- Nature 2016
- Mastering the game of Go with Deep Neural Networks & Tree Search
- A new approach to computer Go that combines Monte-Carlo tree search with deep neural networks that have been trained by supervised learning and reinforcement learning. The first time ever that a computer program has defeated a human professional player.

- Nature 2015
- Human Level Control Through Deep Reinforcement Learning
- This paper describes a Deep Q-Network (DQN), which is able to master a diverse range of Atari 2600 games, through combining Deep Neural Networks with Reinforcement Learning.

- arXiv 2014
- Neural Turing Machines
- Neural Turing Machines (NTMs) couple differentiable, external memory resources to neural network controllers. Unlike classical computers, they can be optimized by stochastic gradient descent to infer algorithms from data.

- ICLR 2016 - Best Paper Award!
- Neural Programmer-Interpreters
- We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural network that learns to represent and execute programs.

- NIPS 2015
- Spatial Transformer Networks
- We introduce a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within a neural network.

- NIPS 2015
- Teaching Machines to Read and Comprehend
- We define a new methodology for capturing large scale supervised reading comprehension data, as well as novel mechanisms for teaching machines to read and comprehend.

- ICML 2016
- Pixel Recurrent Neural Networks
- This paper introduces a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions using novel two-dimensional recurrent layers and an effective use of residual connections in LSTMs.

- Nature 2016
- Mastering the game of Go with Deep Neural Networks & Tree Search
- A new approach to computer Go that combines Monte-Carlo tree search with deep neural networks that have been trained by supervised learning and reinforcement learning. The first time ever that a computer program has defeated a human professional player.

- Nature 2015
- Human Level Control Through Deep Reinforcement Learning
- This paper describes a Deep Q-Network (DQN), which is able to master a diverse range of Atari 2600 games, through combining Deep Neural Networks with Reinforcement Learning.

- arXiv 2014
- Neural Turing Machines
- Neural Turing Machines (NTMs) couple differentiable, external memory resources to neural network controllers. Unlike classical computers, they can be optimized by stochastic gradient descent to infer algorithms from data.

- ICLR 2016 - Best Paper Award!
- Neural Programmer-Interpreters
- We propose the neural programmer-interpreter (NPI): a recurrent and compositional neural network that learns to represent and execute programs.

- NIPS 2015
- Spatial Transformer Networks
- We introduce a new learnable module, the Spatial Transformer, which explicitly allows the spatial manipulation of data within a neural network.

- NIPS 2015
- Teaching Machines to Read and Comprehend
- We define a new methodology for capturing large scale supervised reading comprehension data, as well as novel mechanisms for teaching machines to read and comprehend.

- ICML 2016
- Pixel Recurrent Neural Networks
- This paper introduces a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions using novel two-dimensional recurrent layers and an effective use of residual connections in LSTMs.