Charles H. Martin

Artificial Intelligence · 2018–2019

A researcher in the Science corpus: 2 papers; trusts 261 researchers and is trusted by 4 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 76 citations into it
• Scaling & Learning Theory — 45 citations into it
• Optimization & Training — 32 citations into it
• Computer Vision and Pattern Recognition — 31 citations into it; #13,042 of 21,575 by trust here, #20,756 by citations
• Statistical and Nonlinear Physics — 23 citations into it; #5,461 of 10,127 by trust here, #9,324 by citations
• Statistics and Probability — 16 citations into it; #7,672 of 12,932 by trust here, #11,487 by citations
• Economics and Econometrics — 15 citations into it
• Computational Mechanics — 10 citations into it

Whom Charles H. Martin trusts overall

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

1. Behnam Neyshabur
2. Yoshua Bengio
3. Alex Krizhevsky
4. Yann LeCun
5. Geoffrey E. Hinton
6. Sergey Ioffe
7. Kaiming He
8. Ilya Sutskever
9. Diederik P. Kingma
10. Mark Newman

Who trusts Charles H. Martin overall

1. Thijs Vogels
2. Saisubramaniam Gopalakrishnan
3. Michael W. Mahoney
4. Sai Praneeth Karimireddy
5. Pranshu Ranjan Singh
6. Martin Jaggi

Papers from Charles H. Martin's perspective

Ordered by how strongly the researchers Charles H. Martin 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. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
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

• Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning (2018) — 312 citations
• Heavy-Tailed Universality Predicts Trends in Test Accuracies for Very Large Pre-Trained Deep Neural Networks (2019) — 69 citations