Dmitrii Podoprikhin

Artificial Intelligence · 2015–2018

A researcher in the Science corpus: 6 papers; trusts 228 researchers and is trusted by 58 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 78 citations into it; #4,452 of 35,345 by trust here, #3,457 by citations
• Computer Vision and Pattern Recognition — 54 citations into it; #4,528 of 21,575 by trust here, #3,313 by citations
• Optimization & Training — 39 citations into it; #673 of 2,601 by trust here, #443 by citations
• Model Architectures — 24 citations into it
• Efficiency & Compression — 18 citations into it
• Probabilistic & Bayesian Methods — 8 citations into it
• Representation & Self-Supervised Learning — 8 citations into it
• Computational Theory and Mathematics — 6 citations into it

Whom Dmitrii Podoprikhin trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Karen Simonyan
4. Yann LeCun
5. Kaiming He
6. Yoshua Bengio
7. Diederik P. Kingma
8. Ilya Sutskever
9. Andrew Zisserman
10. Jimmy Ba

Who trusts Dmitrii Podoprikhin overall

1. Pavel Izmailov
2. Yerlan Idelbayev
3. Stanislav Fort
4. Sylvestre-Alvise Rebuffi
5. Sven Gowal
6. Mitchell Wortsman
7. M. A. Carreira-Perpiñán
8. Andrew Gordon Wilson
9. Timur Garipov
10. Jean Kossaifi

Papers from Dmitrii Podoprikhin's perspective

Ordered by how strongly the researchers Dmitrii Podoprikhin 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. Gradient-based learning applied to document recognition
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. ImageNet: A large-scale hierarchical image database
7. Attention is All you Need (Neural Information Processing Systems)
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. Going deeper with convolutions

Their papers

• Averaging Weights Leads to Wider Optima and Better Generalization (2018) — 2,084 citations
• Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs (2018) — 951 citations
• Tensorizing Neural Networks (2015) — 998 citations
• Ultimate tensorization: compressing convolutional and FC layers alike (2016) — 206 citations
• Improving Stability in Deep Reinforcement Learning with Weight Averaging (2018)
• Bayesian Incremental Learning for Deep Neural Networks (2018) — 24 citations