James Lucas

Artificial Intelligence · 2018–2019

A researcher in the Science corpus: 5 papers; trusts 306 researchers and is trusted by 11 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 115 citations into it; #14,825 of 35,345 by trust here, #9,870 by citations
• Computer Vision and Pattern Recognition — 79 citations into it; #9,568 of 21,575 by trust here, #6,606 by citations
• Optimization & Training — 73 citations into it; #2,449 of 2,601 by trust here, #1,154 by citations
• Generative Models — 36 citations into it
• Probabilistic & Bayesian Methods — 29 citations into it
• Model Architectures — 25 citations into it
• Safety, Robustness & Interpretability — 20 citations into it
• Computational Mechanics — 15 citations into it; #4,651 of 10,001 by trust here, #4,749 by citations

Whom James Lucas trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. James Martens
4. Diederik P. Kingma
5. Kaiming He
6. Yoshua Bengio
7. Yann LeCun
8. Ilya Sutskever
9. Boris Polyak
10. Christian Szegedy

Who trusts James Lucas overall

1. Jerry Ma
2. Luke Metz
3. Cem Anil
4. Diganta Misra
5. Huiyu Wang
6. Christopher Fifty
7. Denis Yarats
8. Tianyi Wei
9. Yushu Chen
10. Yan Zhang

Papers from James Lucas's perspective

Ordered by how strongly the researchers James Lucas 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. Gradient-based learning applied to document recognition
6. Attention is All you Need (Neural Information Processing Systems)
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

• Lookahead Optimizer: k steps forward, 1 step back (2019) — 876 citations
• Sorting out Lipschitz function approximation (2018) — 386 citations
• Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapse (2019) — 226 citations
• Aggregated Momentum: Stability Through Passive Damping (2018) — 75 citations
• Adversarial Distillation of Bayesian Neural Network Posteriors (2018) — 61 citations