Pavel Sountsov

Artificial Intelligence · 2016–2020

A researcher in the Science corpus: 3 papers; trusts 145 researchers and is trusted by 6 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 53 citations into it
• Computer Vision and Pattern Recognition — 40 citations into it
• Probabilistic & Bayesian Methods — 35 citations into it
• Generative Models — 32 citations into it
• Natural Language Processing — 18 citations into it; #2,812 of 5,688 by trust here, #4,682 by citations
• Statistics and Probability — 14 citations into it
• Model Architectures — 10 citations into it
• Optimization & Training — 10 citations into it

Whom Pavel Sountsov trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Alex Graves
2. Yoshua Bengio
3. Oriol Vinyals
4. Geoffrey E. Hinton
5. Ilya Sutskever
6. Diederik P. Kingma
7. Radford M. Neal
8. Yann LeCun
9. Alex Krizhevsky
10. Quoc V. Le

Who trusts Pavel Sountsov overall

1. Felix Stahlberg
2. Bryan Eikema
3. Sean Welleck
4. Clara Meister
5. Bill Byrne
6. Wilker Aziz
7. Xinnuo Xu
8. Ilia Kulikov
9. Anjuli Kannan
10. Ryan Cotterell

Papers from Pavel Sountsov's perspective

Ordered by how strongly the researchers Pavel Sountsov trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
9. Learning Multiple Layers of Features from Tiny Images
10. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)

Their papers

• NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport (2019) — 125 citations
• Learning Energy-based Model with Flow-based Backbone by Neural Transport MCMC (2020) — 16 citations
• Length bias in Encoder Decoder Models and a Case for Global Conditioning (2016) — 43 citations