Igor Gitman

Artificial Intelligence · 2017–2019

A researcher in the Science corpus: 7 papers; trusts 366 researchers and is trusted by 661 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 79 citations into it; #3,899 of 35,345 by trust here, #5,638 by citations
• Computer Vision and Pattern Recognition — 52 citations into it; #1,727 of 21,575 by trust here, #4,584 by citations
• Optimization & Training — 49 citations into it; #332 of 2,601 by trust here, #373 by citations
• Natural Language Processing — 38 citations into it
• Model Architectures — 24 citations into it
• Evaluation & Benchmarks — 9 citations into it
• Computational Mechanics — 6 citations into it
• Representation & Self-Supervised Learning — 6 citations into it

Whom Igor Gitman trusts overall

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

1. Alex Krizhevsky
2. Kaiming He
3. Sergey Ioffe
4. Geoffrey E. Hinton
5. Yoshua Bengio
6. Christian Szegedy
7. Diederik P. Kingma
8. Ilya Sutskever
9. Yann LeCun
10. Ross B. Girshick

Who trusts Igor Gitman overall

1. Mahmoud Assran
2. Yang You
3. Elad Hoffer
4. Xinlei Chen
5. Gyuhak Kim
6. Kaiming He
7. Ting-Li Chen
8. Tong Yu
9. Ashok Cutkosky
10. Tal Ben-Nun

Papers from Igor Gitman's perspective

Ordered by how strongly the researchers Igor Gitman 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. ImageNet: A large-scale hierarchical image database
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Large Batch Training of Convolutional Networks (2017) — 967 citations
• OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models (2018) — 33 citations
• Comparison of Batch Normalization and Weight Normalization Algorithms for the Large-scale Image Classification (2017) — 69 citations
• Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq (2018) — 52 citations
• Understanding the Role of Momentum in Stochastic Gradient Methods (2019) — 118 citations
• Large Batch Training of Convolutional Networks with Layer-wise Adaptive Rate Scaling (2018) — 44 citations
• Scaling SGD Batch Size to 32K for ImageNet Training (2017) — 424 citations