Tim Harley
Artificial Intelligence · 2016–2020
A researcher in the Science corpus: 12 papers; trusts 417 researchers and is trusted by 2,099 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 278 citations into it; #622 of 36,961 by trust here, #552 by citations
- Reinforcement Learning — 131 citations into it; #142 of 2,250 by trust here, #60 by citations
- Computer Vision and Pattern Recognition — 116 citations into it; #16,677 of 21,973 by trust here, #6,727 by citations
- Natural Language Processing — 66 citations into it; #4,999 of 5,725 by trust here, #3,260 by citations
- Model Architectures — 54 citations into it; #1,713 of 2,288 by trust here, #318 by citations
- Optimization & Training — 39 citations into it
- Management Science and Operations Research — 33 citations into it; #7,372 of 12,201 by trust here, #312 by citations
- Control and Systems Engineering — 30 citations into it
Whom Tim Harley trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Richard S. Sutton
- Alex Graves
- Yoshua Bengio
- Diederik P. Kingma
- Ilya Sutskever
- Ronald J. Williams
- Alex Krizhevsky
- Sepp Hochreiter
- J. Urgen Schmidhuber
Who trusts Tim Harley overall
- Sergey Levine
- Yuxi Li
- Pieter Abbeel
- Yoshua Bengio
- J. Urgen Schmidhuber
- Ruslan Salakhutdinov
- Emilio Parisotto
- Danijar Hafner
- Trevor Darrell
- Mohammad Norouzi
Papers from Tim Harley's perspective
Ordered by how strongly the researchers Tim Harley 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)
- Attention is All you Need (Neural Information Processing Systems)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Asynchronous Methods for Deep Reinforcement Learning (2016) — 10,169 citations
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures (2018) — 1,890 citations
- Hybrid computing using a neural network with dynamic external memory (2016) — 1,765 citations
- The Predictron: End-To-End Learning and Planning (2016) — 310 citations
- Unsupervised Predictive Memory in a Goal-Directed Agent (2018) — 206 citations
- Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes (2016) — 171 citations
- Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text (2020) — 92 citations
- Imitating Interactive Intelligence (2020) — 74 citations
- Dynamic control flow in large-scale machine learning (2018) — 112 citations
- Robust Instruction-Following in a Situated Agent via Transfer-Learning from Text (2019)
- Multiplicative Interactions and Where to Find Them (2020) — 160 citations
- A Generalized Framework for Population Based Training (2019) — 73 citations