James Harrison

Artificial Intelligence · 2017–2022

A researcher in the Science corpus: 5 papers; trusts 319 researchers and is trusted by 5 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 143 citations into it; #22,526 of 35,345 by trust here, #13,962 by citations
• Reinforcement Learning — 66 citations into it
• Computer Vision and Pattern Recognition — 58 citations into it; #16,722 of 21,575 by trust here, #17,757 by citations
• Optimization & Training — 50 citations into it; #2,189 of 2,601 by trust here, #2,112 by citations
• Meta & Continual Learning — 29 citations into it; #932 of 1,041 by trust here, #766 by citations
• Representation & Self-Supervised Learning — 29 citations into it
• Management Science and Operations Research — 22 citations into it
• Probabilistic & Bayesian Methods — 15 citations into it

Whom James Harrison trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Diederik P. Kingma
2. Sergey Levine
3. Chelsea Finn
4. Geoffrey E. Hinton
5. J. Urgen Schmidhuber
6. Yoshua Bengio
7. Pieter Abbeel
8. Sepp Hochreiter
9. Alex Krizhevsky
10. Richard S. Sutton

Who trusts James Harrison overall

1. Zhenyi Wang
2. Marvin Zhang
3. Massimo Caccia
4. John D. Co-Reyes
5. Haeyong Kang
6. Ahmed Hussain Qureshi
7. Oleksiy Ostapenko
8. Annie Xie
9. Li Shen
10. Pau Rodr'iguez L'opez

Papers from James Harrison's perspective

Ordered by how strongly the researchers James Harrison trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Learning Sampling Distributions for Robot Motion Planning (2017) — 417 citations
• Continuous Meta-Learning without Tasks (2019) — 84 citations
• Deep Reinforcement Learning amidst Lifelong Non-Stationarity (2020) — 73 citations
• Practical tradeoffs between memory, compute, and performance in learned optimizers (2022) — 42 citations
• Deep Reinforcement Learning amidst Continual Structured Non-Stationarity (2021) — 45 citations