Umang Bhatt
Artificial Intelligence · 2019–2023
A researcher in the Science corpus: 9 papers; trusts 88 researchers and is trusted by 2 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 267 citations into it; #26,632 of 35,345 by trust here, #10,798 by citations
- Safety, Robustness & Interpretability — 157 citations into it
- Safety Research — 85 citations into it
- Computer Vision and Pattern Recognition — 60 citations into it
- AI Ethics, Fairness & Society — 55 citations into it
- Probabilistic & Bayesian Methods — 36 citations into it
- Management Science and Operations Research — 30 citations into it
- Sociology and Political Science — 30 citations into it
Whom Umang Bhatt trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Radford M. Neal
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yann LeCun
- Yoshua Bengio
- Alex Krizhevsky
- Lloyd S. Shapley
- Kaiming He
- David John Cameron MacKay
- Ilya Sutskever
Who trusts Umang Bhatt overall
- Javier Antorán
- Adrian Weller
- Vadim Borisov
- Sarah Tan
- Botty Dimanov
- Anamaria Crisan
- Q. Liao
- José M. F. Moura
- Amir-Hossein Karimi
- Tameem Adel
Papers from Umang Bhatt's perspective
Ordered by how strongly the researchers Umang Bhatt 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)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Explainable machine learning in deployment (2019) — 701 citations
- You Shouldn't Trust Me: Learning Models Which Conceal Unfairness From Multiple Explanation Methods (2020) — 110 citations
- Evaluating Language Models for Mathematics through Interactions (2023) — 114 citations
- Harms from Increasingly Agentic Algorithmic Systems (2023) — 259 citations
- Evaluating and Aggregating Feature-based Model Explanations (2020) — 313 citations
- Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty (2020) — 336 citations
- On the Fairness of Causal Algorithmic Recourse (2020) — 105 citations
- Getting a CLUE: A Method for Explaining Uncertainty Estimates (2020) — 135 citations
- Towards Aggregating Weighted Feature Attributions (2019) — 14 citations