Peter S. Dayan
Cognitive Neuroscience · 1990–2020
A researcher in the Science corpus: 62 papers; trusts 997 researchers and is trusted by 9,947 researchers here, as inferred from the citation graph.
Subfields
- Cognitive Neuroscience — 512 citations into it; #11 of 11,026 by trust here, #27 by citations
- Artificial Intelligence — 463 citations into it; #116 of 36,961 by trust here, #575 by citations
- Cellular and Molecular Neuroscience — 247 citations into it; #19 of 3,018 by trust here, #7 by citations
- Reinforcement Learning — 246 citations into it; #29 of 2,250 by trust here, #76 by citations
- Management Science and Operations Research — 116 citations into it; #3,475 of 12,201 by trust here, #6,238 by citations
- Molecular Biology — 96 citations into it; #1,348 of 17,836 by trust here, #4,963 by citations
- Probabilistic & Bayesian Methods — 87 citations into it; #111 of 1,526 by trust here, #76 by citations
- Computer Vision and Pattern Recognition — 79 citations into it; #16,102 of 21,973 by trust here, #9,835 by citations
Whom Peter S. Dayan trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Richard S. Sutton
- Andrew Barto
- Geoffrey E. Hinton
- Nathaniel D. Daw
- Richard S. Zemel
- Radford M. Neal
- J. Urgen Schmidhuber
- Satinder Singh
- Andrew W. Moore
- Ronald J. Williams
Who trusts Peter S. Dayan overall
- Yoshua Bengio
- J. Urgen Schmidhuber
- Sergey Levine
- Ruslan Salakhutdinov
- Danilo Jimenez Rezende
- Karl J. Friston
- Geoffrey E. Hinton
- Satinder Singh
- Quoc V. Le
- Zhe Gan
Papers from Peter S. Dayan's perspective
Ordered by how strongly the researchers Peter S. Dayan trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Q-learning (1992)
- Feudal Reinforcement Learning (1992)
- The Helmholtz Machine (1995)
- The "wake-sleep" algorithm for unsupervised neural networks. (1995)
- Improving Generalization for Temporal Difference Learning: The Successor Representation (1993)
- Efficient Bayes-Adaptive Reinforcement Learning using Sample-Based Search (2012) — 183 citations
- Comparison of Maximum Likelihood and GAN-based training of Real NVPs (2017) — 55 citations
- TD(λ) Converges with Probability 1 (1994)
- Flexible shaping: how learning in small steps helps. (2009) — 252 citations
- Technical Note: Q-Learning (2004) — 2,385 citations
- Fast Parametric Learning with Activation Memorization (2018) — 47 citations
- Varieties of Helmholtz Machine (1996)
- Simple Plans or Sophisticated Habits? State, Transition and Learning Interactions in the Two-Step Task (2015) — 163 citations
- Formalizing Neurath’s Ship: Approximate Algorithms for Online Causal Learning (2016) — 142 citations
- Exploration from Generalization Mediated by Multiple Controllers (2013) — 16 citations
- Static and Dynamic Values of Computation in MCTS (2020) — 7 citations
- Probabilistic Meta-Representations Of Neural Networks (2018) — 29 citations
- Better Optimism By Bayes: Adaptive Planning with Rich Models (2014) — 8 citations
- Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning (2019) — 92 citations
- Dopamine: generalization and bonuses (2002) — 475 citations