Cengiz Pehlevan

Artificial Intelligence · with Bordelon · 2020

A researcher in the Science corpus: 2 papers; trusts 50 researchers and is trusted by 9 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 60 citations into it; #13,115 of 35,345 by trust here, #24,417 by citations
• Scaling & Learning Theory — 44 citations into it; #233 of 428 by trust here, #363 by citations
• Computer Vision and Pattern Recognition — 20 citations into it
• Statistical and Nonlinear Physics — 16 citations into it
• Statistical Learning Theory — 15 citations into it; #658 of 1,038 by trust here, #874 by citations
• Statistics and Probability — 13 citations into it
• Model Architectures — 11 citations into it
• Optimization & Training — 9 citations into it

Whom Cengiz Pehlevan trusts overall

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

1. Peter Sollich
2. Radford M. Neal
3. Christopher K. I. Williams
4. Grace Wahba
5. Carl E. Rasmussen
6. Jaehoon Lee
7. Arthur Jacot
8. Madhu S. Advani
9. Yuhai Wu
10. Yann LeCun

Who trusts Cengiz Pehlevan overall

1. Ryo Karakida
2. Alessandro Favero
3. Shotaro Akaho

Papers from Cengiz Pehlevan's perspective

Ordered by how strongly the researchers Cengiz Pehlevan 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. Gradient-based learning applied to document recognition
3. ImageNet classification with deep convolutional neural networks
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Learning Multiple Layers of Features from Tiny Images
6. Attention is All you Need (Neural Information Processing Systems)
7. Long Short-Term Memory
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. ImageNet: A large-scale hierarchical image database
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks (2020) — 257 citations
• Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks (2020) — 269 citations