Nathan Oken Hodas

Computational Theory and Mathematics · 2012–2018

A researcher in the Science corpus: 13 papers; trusts 331 researchers and is trusted by 29 researchers here, as inferred from the citation graph.

Subfields

• Computational Theory and Mathematics — 116 citations into it; #2,841 of 12,182 by trust here, #1,291 by citations
• Molecular Biology — 113 citations into it; #4,054 of 17,773 by trust here, #6,746 by citations
• Materials Chemistry — 108 citations into it; #1,417 of 11,513 by trust here, #5,386 by citations
• Artificial Intelligence — 102 citations into it; #20,662 of 35,345 by trust here, #16,771 by citations
• Computer Vision and Pattern Recognition — 82 citations into it
• Computational Chemistry & Drug Discovery — 64 citations into it; #350 of 425 by trust here, #380 by citations
• Statistical and Nonlinear Physics — 52 citations into it; #4,000 of 10,127 by trust here, #4,137 by citations
• Model Architectures — 41 citations into it

Whom Nathan Oken Hodas trusts overall

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

1. Kaiming He
2. Yoshua Bengio
3. Geoffrey E. Hinton
4. Diederik P. Kingma
5. Garrett B. Goh
6. Alex Krizhevsky
7. Damon Centola
8. X. Zhang
9. Christian Szegedy
10. Yann LeCun

Who trusts Nathan Oken Hodas overall

1. Garrett B. Goh
2. Kristina Lerman
3. Charles Siegel
4. Abhinav Vishnu
5. Xuhui Meng
6. Emilio Ferrara
7. Gregory Stoddard
8. Tânia F Cova
9. Nazanin Alipourfard
10. Wei Ma

Papers from Nathan Oken Hodas's perspective

Ordered by how strongly the researchers Nathan Oken Hodas 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. Gradient-based learning applied to document recognition
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Going deeper with convolutions
9. Learning Multiple Layers of Features from Tiny Images
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Few-Shot Learning with Metric-Agnostic Conditional Embeddings (2018) — 165 citations
• Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter (2017) — 322 citations
• Deep learning for computational chemistry (2017) — 739 citations
• Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models (2017) — 182 citations
• How Visibility and Divided Attention Constrain Social Contagion (2012) — 141 citations
• SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties (2017) — 166 citations
• How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions? (2017) — 48 citations
• The Simple Rules of Social Contagion (2013) — 313 citations
• Doing the Impossible: Why Neural Networks Can Be Trained at All (2018) — 21 citations
• ChemNet: A Transferable and Generalizable Deep Neural Network for Small-Molecule Property Prediction (2017) — 21 citations
• Dynamic Input Structure and Network Assembly for Few-Shot Learning (2017) — 5 citations
• Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systems (2017) — 479 citations
• Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction (2017) — 100 citations