Andrew Gordon Wilson
Artificial Intelligence · 2010–2023
A researcher in the Science corpus: 43 papers; trusts 2,658 researchers and is trusted by 1,502 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,128 citations into it; #949 of 36,961 by trust here, #1,364 by citations
- Computer Vision and Pattern Recognition — 587 citations into it; #1,900 of 21,973 by trust here, #1,649 by citations
- Optimization & Training — 226 citations into it; #430 of 2,605 by trust here, #370 by citations
- Probabilistic & Bayesian Methods — 218 citations into it; #123 of 1,526 by trust here, #123 by citations
- Representation & Self-Supervised Learning — 184 citations into it; #1,367 of 3,156 by trust here, #1,220 by citations
- Statistics and Probability — 140 citations into it
- Model Architectures — 128 citations into it; #1,708 of 2,288 by trust here, #1,495 by citations
- Computational Theory and Mathematics — 100 citations into it; #732 of 12,489 by trust here, #1,724 by citations
Whom Andrew Gordon Wilson trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Radford M. Neal
- Geoffrey E. Hinton
- Alex Krizhevsky
- Diederik P. Kingma
- Kaiming He
- Yoshua Bengio
- Yann LeCun
- David John Cameron MacKay
- Iain Murray
- Ilya Sutskever
Who trusts Andrew Gordon Wilson overall
- Pavel Izmailov
- Haitao Liu
- Maruan Al-Shedivat
- Zhiting Hu
- Hannes Nickisch
- Eric P. Xing
- Ruslan Salakhutdinov
- Zoubin Ghahramani
- Andreas Holzinger
- Jacob V. Gardner
Papers from Andrew Gordon Wilson's perspective
Ordered by how strongly the researchers Andrew Gordon Wilson 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
- 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
- Averaging Weights Leads to Wider Optima and Better Generalization (2018) — 2,084 citations
- Deep Kernel Learning (2015) — 1,081 citations
- Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs (2018) — 951 citations
- There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average (2018) — 262 citations
- Gaussian Process Kernels for Pattern Discovery and Extrapolation (2013) — 682 citations
- Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP) (2015) — 579 citations
- A la Carte - Learning Fast Kernels (2014) — 139 citations
- Stochastic Variational Deep Kernel Learning (2016) — 301 citations
- A Simple Baseline for Bayesian Uncertainty in Deep Learning (2019) — 1,004 citations
- Gaussian Process Regression Networks (2011) — 209 citations
- Simple Black-box Adversarial Attacks (2019) — 714 citations
- Learning Scalable Deep Kernels with Recurrent Structure (2016) — 116 citations
- Student-t Processes as Alternatives to Gaussian Processes (2014) — 227 citations
- Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data (2020) — 396 citations
- Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning (2019) — 298 citations
- Bayesian Deep Learning and a Probabilistic Perspective of Generalization (2020) — 816 citations
- Bayesian GAN (2017) — 151 citations
- Does Knowledge Distillation Really Work? (2021) — 292 citations
- GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration (2018) — 1,460 citations
- Thoughts on Massively Scalable Gaussian Processes (2015) — 116 citations