Preetum Nakkiran

Artificial Intelligence · 2015–2019

A researcher in the Science corpus: 6 papers; trusts 47 researchers and is trusted by 25 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 77 citations into it; #7,511 of 35,345 by trust here, #7,797 by citations
• Computer Vision and Pattern Recognition — 37 citations into it
• Scaling & Learning Theory — 35 citations into it
• Optimization & Training — 20 citations into it
• Signal Processing — 17 citations into it; #3,621 of 7,572 by trust here, #3,673 by citations
• Safety, Robustness & Interpretability — 16 citations into it; #633 of 2,251 by trust here, #1,780 by citations
• Computational Mechanics — 10 citations into it
• Natural Language Processing — 10 citations into it

Whom Preetum Nakkiran trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Kaiming He
4. Yoshua Bengio
5. Peter L. Bartlett
6. Yann LeCun
7. Ilya Sutskever
8. Diederik P. Kingma
9. Tara N. Sainath
10. Alex Graves

Who trusts Preetum Nakkiran overall

1. Akshay Degwekar
2. Cihang Xie
3. Rohit Prabhavalkar
4. Vinod Vaikuntanathan
5. Bharat Bhusan Sau
6. Aditi Raghunathan
7. Xavier Suau
8. Andrew Ilyas
9. Alan L. Yuille
10. Eric Wong

Papers from Preetum Nakkiran's perspective

Ordered by how strongly the researchers Preetum Nakkiran 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. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Attention is All you Need (Neural Information Processing Systems)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. Learning Multiple Layers of Features from Tiny Images
8. ImageNet: A large-scale hierarchical image database
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

• Adversarial Robustness May Be at Odds With Simplicity (2019) — 116 citations
• Deep double descent: where bigger models and more data hurt (2019) — 1,162 citations
• SGD on Neural Networks Learns Functions of Increasing Complexity (2019) — 301 citations
• Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks (2015) — 93 citations
• Compressing deep neural networks using a rank-constrained topology (2015) — 81 citations
• A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features': Adversarial Examples are Just Bugs, Too (2019) — 28 citations