Itay Safran

Artificial Intelligence · 2015–2019

A researcher in the Science corpus: 5 papers; trusts 101 researchers and is trusted by 41 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 60 citations into it; #4,923 of 35,345 by trust here, #8,439 by citations
• Safety, Robustness & Interpretability — 25 citations into it
• Computer Vision and Pattern Recognition — 24 citations into it; #7,367 of 21,575 by trust here, #10,010 by citations
• Optimization & Training — 19 citations into it; #1,048 of 2,601 by trust here, #1,349 by citations
• Model Architectures — 13 citations into it
• Scaling & Learning Theory — 12 citations into it
• Computational Mechanics — 8 citations into it; #1,399 of 10,001 by trust here, #1,867 by citations
• Statistical Learning Theory — 8 citations into it; #498 of 1,038 by trust here, #488 by citations

Whom Itay Safran trusts overall

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

1. Yoshua Bengio
2. Geoffrey E. Hinton
3. Kaiming He
4. Alex Krizhevsky
5. Francis R. Bach
6. Yann LeCun
7. Rong Ge
8. Ilya Sutskever
9. Diederik P. Kingma
10. Ian J. Goodfellow

Who trusts Itay Safran overall

1. Simon Shaolei Du
2. Luca Venturi
3. Sanjeev Arora
4. Samet Oymak
5. Joan Bruna
6. Jason D. Lee
7. Elad Hoffer
8. Or Sharir
9. Philipp Christian Petersen
10. Xiao Zhang

Papers from Itay Safran's perspective

Ordered by how strongly the researchers Itay Safran 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. 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

• On the Quality of the Initial Basin in Overspecified Neural Networks (2015) — 131 citations
• Spurious Local Minima are Common in Two-Layer ReLU Neural Networks (2017) — 286 citations
• A Simple Explanation for the Existence of Adversarial Examples with Small Hamming Distance (2019) — 97 citations
• Depth-Width Tradeoffs in Approximating Natural Functions with Neural Networks (2016) — 186 citations
• Depth Separation in ReLU Networks for Approximating Smooth Non-Linear Functions (2016) — 32 citations