Kevin Swersky
Artificial Intelligence · 2010–2024
A researcher in the Science corpus: 30 papers; trusts 2,160 researchers and is trusted by 7,361 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 694 citations into it; #241 of 36,961 by trust here, #343 by citations
- Computer Vision and Pattern Recognition — 352 citations into it; #689 of 21,973 by trust here, #978 by citations
- Representation & Self-Supervised Learning — 168 citations into it; #60 of 3,156 by trust here, #77 by citations
- Probabilistic & Bayesian Methods — 121 citations into it; #188 of 1,526 by trust here, #64 by citations
- Management Science and Operations Research — 105 citations into it; #365 of 12,201 by trust here, #273 by citations
- Optimization & Training — 95 citations into it; #214 of 2,605 by trust here, #229 by citations
- Computational Theory and Mathematics — 82 citations into it; #352 of 12,489 by trust here, #144 by citations
- Statistics and Probability — 78 citations into it
Whom Kevin Swersky trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Diederik P. Kingma
- Yoshua Bengio
- Ruslan Salakhutdinov
- Yann LeCun
- Ilya Sutskever
- Radford M. Neal
- Kaiming He
- Jasper Snoek
Who trusts Kevin Swersky overall
- Yoshua Bengio
- Frank Hutter
- Han-Jia Ye
- Aaron Klein
- Stefan Falkner
- Kyunghyun Cho
- Sergey Levine
- Ruslan Salakhutdinov
- Bernt Schiele
- Trevor Darrell
Papers from Kevin Swersky's perspective
Ordered by how strongly the researchers Kevin Swersky 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)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Prototypical Networks for Few-shot Learning (2017) — 10,206 citations
- Big Self-Supervised Models are Strong Semi-Supervised Learners (2020) — 2,576 citations
- Generative Moment Matching Networks (2015) — 936 citations
- Meta-Learning for Semi-Supervised Few-Shot Classification (2018) — 1,444 citations
- Scalable Bayesian Optimization Using Deep Neural Networks (2015) — 1,144 citations
- Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions (2015) — 452 citations
- Learning Fair Representations (2013) — 2,047 citations
- Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (2019) — 701 citations
- Taking the Human Out of the Loop: A Review of Bayesian Optimization (2016) — 5,660 citations
- Multi-Task Bayesian Optimization (2013) — 842 citations
- Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One (2019) — 664 citations
- Input Warping for Bayesian Optimization of Non-Stationary Functions (2014) — 265 citations
- Freeze-Thaw Bayesian Optimization (2014) — 293 citations
- Inductive Principles for Restricted Boltzmann Machine Learning (2010) — 167 citations
- On Autoencoders and Score Matching for Energy Based Models (2011) — 98 citations
- Estimating the Hessian by Back-propagating Curvature (2012) — 87 citations
- Raiders of the Lost Architecture: Kernels for Bayesian Optimization in Conditional Parameter Spaces (2014) — 84 citations
- Flexibly Fair Representation Learning by Disentanglement (2019) — 383 citations
- Graph Normalizing Flows (2019) — 187 citations
- Learning unbiased features (2014) — 73 citations