| Unified Scaling Laws for Routed Language Models. | 0 | 0.34 | 2022 |
| Improved protein structure prediction using potentials from deep learning. | 36 | 1.10 | 2020 |
| Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning | 0 | 0.34 | 2020 |
| The StreetLearn Environment and Dataset. | 0 | 0.34 | 2019 |
| Human-level performance in first-person multiplayer games with population-based deep reinforcement learning. | 28 | 0.73 | 2018 |
| IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures. | 67 | 1.67 | 2018 |
| Vector-based navigation using grid-like representations in artificial agents. | 27 | 1.26 | 2018 |
| Unsupervised Predictive Memory in a Goal-Directed Agent. | 13 | 0.87 | 2018 |
| Parallel WaveNet: Fast High-Fidelity Speech Synthesis. | 40 | 1.31 | 2018 |
| Learning to Navigate in Cities Without a Map. | 17 | 0.60 | 2018 |
| Efficient Neural Audio Synthesis. | 14 | 0.62 | 2018 |
| FeUdal Networks for Hierarchical Reinforcement Learning. | 65 | 1.68 | 2017 |
| Video Pixel Networks. | 0 | 0.34 | 2017 |
| Hierarchical Representations for Efficient Architecture Search. | 70 | 1.90 | 2017 |
| Understanding Synthetic Gradients and Decoupled Neural Interfaces. | 9 | 0.48 | 2017 |
| Decoupled Neural Interfaces using Synthetic Gradients. | 38 | 1.12 | 2017 |
| Population Based Training of Neural Networks. | 55 | 2.16 | 2017 |
| Automated Curriculum Learning for Neural Networks. | 33 | 1.05 | 2017 |
| Neural Discrete Representation Learning | 50 | 1.17 | 2017 |
| Combining policy gradient and Q-learning | 30 | 1.38 | 2017 |
| Interaction Networks for Learning about Objects, Relations and Physics. | 23 | 0.63 | 2016 |
| Attend, Infer, Repeat: Fast Scene Understanding with Generative Models | 0 | 0.34 | 2016 |
| Sample Efficient Actor-Critic with Experience Replay. | 4 | 0.43 | 2016 |
| Exploiting Cyclic Symmetry in Convolutional Neural Networks. | 29 | 1.11 | 2016 |
| Conditional Image Generation with PixelCNN Decoders. | 199 | 7.17 | 2016 |
| Progressive Neural Networks. | 0 | 0.34 | 2016 |
| Pixel Recurrent Neural Networks. | 224 | 7.32 | 2016 |
| Hybrid computing using a neural network with dynamic external memory. | 80 | 2.86 | 2016 |
| What is the Best Feature Learning Procedure in Hierarchical Recognition Architectures? | 0 | 0.34 | 2016 |
| Strategic Attentive Writer for Learning Macro-Actions. | 28 | 1.37 | 2016 |
| Mastering the game of Go with deep neural networks and tree search. | 1643 | 63.63 | 2016 |
| Neural Machine Translation in Linear Time. | 77 | 2.16 | 2016 |
| Reinforcement Learning with Unsupervised Auxiliary Tasks. | 10 | 0.48 | 2016 |
| Matching Networks for One Shot Learning. | 280 | 6.74 | 2016 |
| Asynchronous Methods for Deep Reinforcement Learning. | 594 | 19.98 | 2016 |
| WaveNet: A Generative Model for Raw Audio. | 358 | 11.09 | 2016 |
| Learning to Navigate in Complex Environments. | 14 | 0.56 | 2016 |
| Massively Parallel Methods for Deep Reinforcement Learning | 83 | 5.85 | 2015 |
| Policy Distillation. | 0 | 0.34 | 2015 |
| Multiple Object Recognition with Visual Attention | 0 | 0.34 | 2015 |
| Human-level control through deep reinforcement learning. | 2197 | 87.20 | 2015 |
| Spatial Transformer Networks | 526 | 14.30 | 2015 |
| Weight Uncertainty in Neural Networks | 145 | 5.35 | 2015 |
| Natural Neural Networks | 0 | 0.34 | 2015 |
| Unsupervised Feature Learning by Deep Sparse Coding. | 0 | 0.34 | 2014 |
| Multiple Object Recognition with Visual Attention. | 161 | 7.91 | 2014 |
| Recurrent Models of Visual Attention. | 362 | 17.72 | 2014 |
| Learning word embeddings efficiently with noise-contrastive estimation. | 96 | 6.83 | 2013 |
| Unsupervised Feature Learning by Deep Sparse Coding. | 16 | 0.59 | 2013 |
| Playing Atari with Deep Reinforcement Learning. | 668 | 25.80 | 2013 |
