Sujay Sanghavi
Artificial Intelligence · with Shah · 2018–2020
A researcher in the Science corpus: 2 papers; trusts 69 researchers and is trusted by 12 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 41 citations into it
- Optimization & Training — 24 citations into it; #1,270 of 2,601 by trust here, #1,624 by citations
- Statistics and Probability — 18 citations into it
- Computer Vision and Pattern Recognition — 15 citations into it
- Computational Mechanics — 14 citations into it
- Safety, Robustness & Interpretability — 13 citations into it; #903 of 2,251 by trust here, #1,673 by citations
- Signal Processing — 6 citations into it
- Statistical Learning Theory — 5 citations into it
Whom Sujay Sanghavi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Yann LeCun
- Yoshua Bengio
- Kaiming He
- Geoffrey E. Hinton
- Sivaraman Balakrishnan
- Sainbayar Sukhbaatar
- Alec Radford
- Simon S. Haykin
- Rob Fergus
Who trusts Sujay Sanghavi overall
Papers from Sujay Sanghavi's perspective
Ordered by how strongly the researchers Sujay Sanghavi trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet: A large-scale hierarchical image database
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Choosing the Sample with Lowest Loss makes SGD Robust (2020) — 51 citations
- Learning with Bad Training Data via Iterative Trimmed Loss Minimization (2018) — 297 citations