Tom McGrath

Artificial Intelligence · 2018–2021

A researcher in the Science corpus: 3 papers; trusts 7 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 80 citations into it
• Optimization & Training — 16 citations into it
• Natural Language Processing — 14 citations into it
• Safety, Robustness & Interpretability — 14 citations into it
• Management Science and Operations Research — 9 citations into it
• Information Systems — 6 citations into it
• Probabilistic & Bayesian Methods — 6 citations into it
• Statistics and Probability — 6 citations into it

Whom Tom McGrath trusts overall

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

1. Diederik P. Kingma

Papers from Tom McGrath's perspective

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

1. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
2. Long Short-Term Memory
3. Asynchronous Methods for Deep Reinforcement Learning
4. Reinforcement Learning: An Introduction
5. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
6. Playing Atari with Deep Reinforcement Learning (arXiv.org)
7. Language Models are Few-Shot Learners (Neural Information Processing Systems)
8. Matching Networks for One Shot Learning
9. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
10. ImageNet classification with deep convolutional neural networks

Their papers

• Causal Analysis of Agent Behavior for AI Safety (2021) — 8 citations
• Meta-learning of Sequential Strategies (2019) — 120 citations
• FHI Oxford Technical Report # 2018-2 Predicting Human Deliberative Judgments with Machine Learning (2018)