Soumik Mandal

Artificial Intelligence · 2018

A researcher in the Science corpus: 3 papers; trusts 42 researchers and is trusted by 20 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 47 citations into it; #9,645 of 35,345 by trust here, #6,103 by citations
• Statistical Learning Theory — 25 citations into it
• Scaling & Learning Theory — 25 citations into it; #138 of 428 by trust here, #121 by citations
• Computer Vision and Pattern Recognition — 23 citations into it; #9,104 of 21,575 by trust here, #8,612 by citations
• Optimization & Training — 14 citations into it
• Statistics and Probability — 13 citations into it
• Model Architectures — 12 citations into it
• Computational Mechanics — 10 citations into it; #3,530 of 10,001 by trust here, #2,203 by citations

Whom Soumik Mandal trusts overall

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

1. Mikhail Belkin
2. Alex Krizhevsky
3. Peter L. Bartlett
4. Jerome H. Friedman
5. Siyuan Ma
6. Yann LeCun
7. Vladimir Naumovich Vapni
8. Yoshua Bengio
9. Geoffrey E. Hinton
10. Trevor J. Hastie

Who trusts Soumik Mandal overall

1. Mikhail Belkin
2. Tengyuan Liang
3. Vitaly Feldman
4. Chaoyue Liu
5. Partha P. Mitra
6. Aditi Raghunathan
7. Yamini Bansal

Papers from Soumik Mandal's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Gradient-based learning applied to document recognition
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
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. Going deeper with convolutions

Their papers

• Reconciling modern machine-learning practice and the classical bias–variance trade-off (2018) — 2,107 citations
• To understand deep learning we need to understand kernel learning (2018) — 446 citations
• Reconciling modern machine learning and the bias-variance trade-off (2018) — 136 citations