Yarin Gal
Artificial Intelligence · 2014–2024
A researcher in the Science corpus: 37 papers; trusts 3,404 researchers and is trusted by 6,715 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 931 citations into it; #194 of 36,961 by trust here, #458 by citations
- Computer Vision and Pattern Recognition — 448 citations into it; #1,291 of 21,973 by trust here, #1,851 by citations
- Probabilistic & Bayesian Methods — 254 citations into it; #15 of 1,526 by trust here, #29 by citations
- Optimization & Training — 142 citations into it; #107 of 2,605 by trust here, #306 by citations
- Statistics and Probability — 107 citations into it
- Reinforcement Learning — 100 citations into it
- Model Architectures — 99 citations into it; #344 of 2,288 by trust here, #1,115 by citations
- Natural Language Processing — 90 citations into it
Whom Yarin Gal trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Yann LeCun
- Alex Graves
- Geoffrey E. Hinton
- Alex Krizhevsky
- Yoshua Bengio
- Radford M. Neal
- Ilya Sutskever
- Kaiming He
- Max Welling
Who trusts Yarin Gal overall
- Alex Kendall
- Sergey Levine
- Andrey Malinin
- Yoshua Bengio
- Sebastian Farquhar
- Yingzhen Li
- Qiang Liu
- S. Murray
- Chunyuan Li
- Quoc V. Le
Papers from Yarin Gal's perspective
Ordered by how strongly the researchers Yarin Gal 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning (2015) — 12,300 citations
- A Theoretically Grounded Application of Dropout in Recurrent Neural Networks (2015) — 1,727 citations
- Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics (2017) — 4,210 citations
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? (2017) — 6,295 citations
- Deep Bayesian Active Learning with Image Data (2017) — 2,034 citations
- Towards Robust Evaluations of Continual Learning (2018) — 329 citations
- Real Time Image Saliency for Black Box Classifiers (2017) — 638 citations
- Concrete Dropout (2017) — 677 citations
- Learning Invariant Representations for Reinforcement Learning without Reconstruction (2020) — 593 citations
- Dropout Inference in Bayesian Neural Networks with Alpha-divergences (2017) — 215 citations
- Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam (2018) — 296 citations
- Invariant Causal Prediction for Block MDPs (2020) — 159 citations
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference (2015) — 829 citations
- Distributed Variational Inference in Sparse Gaussian Process Regression and Latent Variable Models (2014) — 154 citations
- The Curse of Recursion: Training on Generated Data Makes Models Forget (2023) — 507 citations
- Understanding Measures of Uncertainty for Adversarial Example Detection (2018) — 421 citations
- BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning (2019) — 777 citations
- Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation (2023) — 830 citations
- VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning (2019) — 331 citations
- Concrete Problems for Autonomous Vehicle Safety: Advantages of Bayesian Deep Learning (2017) — 345 citations