Philip J. Ball

Artificial Intelligence · 2019–2023

A researcher in the Science corpus: 4 papers; trusts 93 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 118 citations into it
• Reinforcement Learning — 90 citations into it
• Computer Vision and Pattern Recognition — 26 citations into it
• Computational Theory and Mathematics — 16 citations into it
• Management Science and Operations Research — 15 citations into it
• Optimization & Training — 15 citations into it
• Control and Systems Engineering — 13 citations into it
• Probabilistic & Bayesian Methods — 10 citations into it

Whom Philip J. Ball trusts overall

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

1. Sergey Levine
2. Richard S. Sutton
3. Geoffrey E. Hinton
4. J. Urgen Schmidhuber
5. John Schulman
6. Diederik P. Kingma
7. Alex Krizhevsky
8. Yoshua Bengio
9. Pieter Abbeel
10. David John Cameron MacKay

Who trusts Philip J. Ball overall

1. Jack Parker-Holder
2. Samuel Kessler
3. Aldo Pacchiano

Papers from Philip J. Ball's perspective

Ordered by how strongly the researchers Philip J. Ball 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. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Ready Policy One: World Building Through Active Learning (2020) — 54 citations
• Same State, Different Task: Continual Reinforcement Learning without Interference (2021) — 62 citations
• The Sensitivity of Counterfactual Fairness to Unmeasured Confounding (2019) — 65 citations
• Efficient Online Reinforcement Learning with Offline Data (2023) — 401 citations