Geoffrey E. Hinton
Artificial Intelligence · 1979–2022
A researcher in the Science corpus: 186 papers; trusts 4,270 researchers and is trusted by 45,688 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,608 citations into it; #1 of 36,961 by trust here, #1 by citations
- Computer Vision and Pattern Recognition — 1,184 citations into it; #3 of 21,973 by trust here, #5 by citations
- Model Architectures — 332 citations into it; #10 of 2,288 by trust here, #15 by citations
- Representation & Self-Supervised Learning — 331 citations into it; #2 of 3,156 by trust here, #2 by citations
- Natural Language Processing — 310 citations into it; #33 of 5,725 by trust here, #37 by citations
- Optimization & Training — 288 citations into it; #10 of 2,605 by trust here, #6 by citations
- Probabilistic & Bayesian Methods — 261 citations into it; #1 of 1,526 by trust here, #1 by citations
- Signal Processing — 226 citations into it; #1 of 7,592 by trust here, #2 by citations
Whom Geoffrey E. Hinton trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Yoshua Bengio
- Ruslan Salakhutdinov
- Radford M. Neal
- Kaiming He
- Diederik P. Kingma
- Max Welling
- Yann LeCun
- Alex Graves
- Ilya Sutskever
Who trusts Geoffrey E. Hinton overall
- Yoshua Bengio
- Ruslan Salakhutdinov
- Kyunghyun Cho
- Li Deng
- Quoc V. Le
- Aaron C. Courville
- Kaiming He
- Zhe Gan
- Marc'Aurelio Ranzato
- Dacheng Tao
Papers from Geoffrey E. Hinton's perspective
Ordered by how strongly the researchers Geoffrey E. Hinton 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
- ImageNet classification with deep convolutional neural networks (2012) — 130,310 citations
- Dropout: a simple way to prevent neural networks from overfitting (2014) — 43,754 citations
- Visualizing Data using t-SNE (2008) — 50,192 citations
- Rectified Linear Units Improve Restricted Boltzmann Machines (2010) — 18,880 citations
- Distilling the Knowledge in a Neural Network (2015) — 25,160 citations
- Layer Normalization (2016) — 12,877 citations
- A Fast Learning Algorithm for Deep Belief Nets (2006) — 16,970 citations
- Improving neural networks by preventing co-adaptation of feature detectors (2012) — 8,038 citations
- Learning representations by back-propagating errors (1986)
- Speech recognition with deep recurrent neural networks (2013) — 9,035 citations
- A Simple Framework for Contrastive Learning of Visual Representations (2020) — 25,300 citations
- Training Products of Experts by Minimizing Contrastive Divergence (2002) — 5,632 citations
- On the importance of initialization and momentum in deep learning (2013) — 5,312 citations
- Learning internal representations by error propagation (1986)
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups (2012) — 3,180 citations
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (2017) — 5,113 citations
- Generating Text with Recurrent Neural Networks (2011) — 1,560 citations
- Deep Boltzmann Machines (2009) — 2,353 citations
- Adaptive Mixtures of Local Experts (1991)
- Grammar as a Foreign Language (2014) — 942 citations