Steven M. Kearnes

Computational Theory and Mathematics · 2015–2018

A researcher in the Science corpus: 9 papers; trusts 19 researchers and is trusted by 41 researchers here, as inferred from the citation graph.

Subfields

• Computational Theory and Mathematics — 91 citations into it; #1,196 of 12,182 by trust here, #140 by citations
• Molecular Biology — 65 citations into it
• Materials Chemistry — 63 citations into it; #720 of 11,513 by trust here, #1,687 by citations
• Computational Chemistry & Drug Discovery — 57 citations into it; #76 of 425 by trust here, #51 by citations
• Artificial Intelligence — 48 citations into it
• Evaluation & Benchmarks — 21 citations into it
• Statistics and Probability — 6 citations into it

Whom Steven M. Kearnes trusts overall

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

1. Sereina Riniker
2. Peter Willett
3. Michael M. Mysinger
4. Tom Fawcett
5. Geoffrey E. Hinton
6. R. Caruana
7. Ajay N. Jain
8. Jonathan Masci
9. Anthony Nicholls
10. George E. Dahl

Who trusts Steven M. Kearnes overall

1. Garrett B. Goh
2. Wengong Jin
3. Charles Siegel
4. Mukund Sundararajan
5. Abhinav Vishnu
6. Kyle Swanson
7. Regina Barzilay
8. Nathan Oken Hodas
9. Yuanqi Du
10. Esben Jannik Bjerrum

Papers from Steven M. Kearnes's perspective

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

Their papers

• Tensor Field Networks: Rotation- and Translation-Equivariant Neural Networks for 3D Point Clouds (2018) — 1,225 citations
• Molecular graph convolutions: moving beyond fingerprints (2016) — 1,608 citations
• Massively Multitask Networks for Drug Discovery (2015) — 499 citations
• Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error. (2017) — 593 citations
• Modeling Industrial ADMET Data with Multitask Networks (2016) — 58 citations
• Optimization of Molecules via Deep Reinforcement Learning (2018) — 665 citations
• Fast machine learning models of electronic and energetic properties consistently reach approximation errors better than DFT accuracy (2017) — 19 citations
• Machine learning prediction errors better than DFT accuracy (2017) — 36 citations
• ROCS-derived features for virtual screening (2016) — 30 citations