Maithra Raghu
Artificial Intelligence · 2016–2021
A researcher in the Science corpus: 14 papers; trusts 2,304 researchers and is trusted by 329 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 444 citations into it; #1,975 of 36,961 by trust here, #2,166 by citations
- Computer Vision and Pattern Recognition — 305 citations into it; #9,509 of 21,973 by trust here, #5,221 by citations
- Representation & Self-Supervised Learning — 105 citations into it; #716 of 3,156 by trust here, #682 by citations
- Model Architectures — 77 citations into it; #541 of 2,288 by trust here, #446 by citations
- Safety, Robustness & Interpretability — 65 citations into it; #1,169 of 2,259 by trust here, #759 by citations
- Natural Language Processing — 64 citations into it
- Optimization & Training — 51 citations into it
- Radiology, Nuclear Medicine and Imaging — 36 citations into it
Whom Maithra Raghu trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Diederik P. Kingma
- Ilya Sutskever
- Karen Simonyan
- Yann LeCun
- Ross B. Girshick
- Christian Szegedy
Who trusts Maithra Raghu overall
- Simon Kornblith
- Boris Hanin
- Ari S. Morcos
- Thao Nguyen
- Yoshua Bengio
- Aniruddh Raghu
- Chiyuan Zhang
- Samy Bengio
- Yonatan Belinkov
- Greg Yang
Papers from Maithra Raghu's perspective
Ordered by how strongly the researchers Maithra Raghu trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- On the Expressive Power of Deep Neural Networks (2016) — 897 citations
- Adversarial Spheres (2018) — 358 citations
- Exponential expressivity in deep neural networks through transient chaos (2016) — 683 citations
- Insights on representational similarity in neural networks with canonical correlation (2018) — 564 citations
- Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML (2019) — 756 citations
- Transfusion: Understanding Transfer Learning for Medical Imaging (2019) — 1,299 citations
- Do Vision Transformers See Like Convolutional Neural Networks? (2021) — 1,440 citations
- Transfusion: Understanding Transfer Learning with Applications to Medical Imaging (2019) — 95 citations
- SVCCA: Singular Vector Canonical Correlation Analysis for Deep Understanding and Improvement (2017) — 36 citations
- Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics (2020) — 216 citations
- Do Wide and Deep Networks Learn the Same Things? Uncovering How Neural Network Representations Vary with Width and Depth (2020) — 340 citations
- A Survey of Deep Learning for Scientific Discovery (2020) — 155 citations
- Direct Uncertainty Prediction for Medical Second Opinions (2018) — 156 citations
- SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability (2017) — 906 citations