Roman Novak

Artificial Intelligence · 2016–2023

A researcher in the Science corpus: 13 papers; trusts 341 researchers and is trusted by 62 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 194 citations into it; #3,938 of 35,345 by trust here, #2,534 by citations
• Computer Vision and Pattern Recognition — 116 citations into it; #6,249 of 21,575 by trust here, #8,722 by citations
• Scaling & Learning Theory — 70 citations into it; #194 of 428 by trust here, #101 by citations
• Optimization & Training — 65 citations into it
• Model Architectures — 59 citations into it; #697 of 2,278 by trust here, #635 by citations
• Probabilistic & Bayesian Methods — 39 citations into it; #621 of 1,525 by trust here, #244 by citations
• Statistical Learning Theory — 31 citations into it
• Statistical and Nonlinear Physics — 31 citations into it; #1,495 of 10,127 by trust here, #806 by citations

Whom Roman Novak trusts overall

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

1. Alex Krizhevsky
2. Geoffrey E. Hinton
3. Yoshua Bengio
4. Karen Simonyan
5. Diederik P. Kingma
6. Yann LeCun
7. Ronan Collobert
8. Kaiming He
9. Ilya Sutskever
10. Radford M. Neal

Who trusts Roman Novak overall

1. Greg Yang
2. Lechao Xiao
3. Timothy Nguyen
4. Jaehoon Lee
5. Agnieszka Mikołajczyk
6. Jascha Narain Sohl-Dickstein
7. Yasaman Bahri
8. Michal Grochowski
9. Sam Schoenholz
10. Soufiane Hayou

Papers from Roman Novak's perspective

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

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

Their papers

• Wide neural networks of any depth evolve as linear models under gradient descent (2019) — 1,337 citations
• Deep Neural Networks as Gaussian Processes (2017) — 1,255 citations
• Sensitivity and Generalization in Neural Networks: an Empirical Study (2018) — 514 citations
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes (2018) — 331 citations
• Iterative Refinement for Machine Translation (2016) — 29 citations
• Dataset Distillation with Infinitely Wide Convolutional Networks (2021) — 307 citations
• Neural Tangents: Fast and Easy Infinite Neural Networks in Python (2019) — 261 citations
• Exploring the Neural Algorithm of Artistic Style (2016) — 40 citations
• Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models (2023) — 337 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2023) — 266 citations
• Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
• On the infinite width limit of neural networks with a standard parameterization (2020) — 56 citations
• Improving the Neural Algorithm of Artistic Style (2016) — 33 citations