Jeremy Bernstein

Artificial Intelligence · 2018–2020

A researcher in the Science corpus: 4 papers; trusts 65 researchers and is trusted by 33 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 65 citations into it; #9,104 of 35,345 by trust here, #5,788 by citations
• Optimization & Training — 52 citations into it; #667 of 2,601 by trust here, #680 by citations
• Computer Vision and Pattern Recognition — 30 citations into it
• Computational Mechanics — 16 citations into it; #2,193 of 10,001 by trust here, #1,249 by citations
• Safety, Robustness & Interpretability — 13 citations into it
• Model Architectures — 10 citations into it
• Management Science and Operations Research — 7 citations into it

Whom Jeremy Bernstein trusts overall

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

1. Alex Krizhevsky
2. Kaiming He
3. Geoffrey E. Hinton
4. Yann LeCun
5. Diederik P. Kingma
6. Yoshua Bengio
7. X. Zhang
8. Jia Deng
9. Ilya Sutskever
10. Jimmy Ba

Who trusts Jeremy Bernstein overall

1. Sai Praneeth Karimireddy
2. Xiangyi Chen
3. Shuai Zheng
4. Martin Jaggi
5. Thijs Vogels
6. Felix Sattler
7. Jy-yong Sohn
8. Cong Xie
9. Ahmed Khaled
10. Lie He

Papers from Jeremy Bernstein's perspective

Ordered by how strongly the researchers Jeremy Bernstein 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. ImageNet: A large-scale hierarchical image database
6. Long Short-Term Memory
7. Attention is All you Need (Neural Information Processing Systems)
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

• signSGD: compressed optimisation for non-convex problems (2018) — 1,323 citations
• Stochastic Activation Pruning for Robust Adversarial Defense (2018) — 581 citations
• On the distance between two neural networks and the stability of learning (2020) — 75 citations
• signSGD with Majority Vote is Communication Efficient and Fault Tolerant (2018) — 314 citations