Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Nathan O. Hodas

Nathan O. Hodas

Pacific Northwest National Laboratory

Adaptive Transfer Learning: a simple but effective transfer learning


Nov 22, 2021
Jung H Lee, Henry J Kvinge, Scott Howland, Zachary New, John Buckheit, Lauren A. Phillips, Elliott Skomski, Jessica Hibler, Courtney D. Corley, Nathan O. Hodas

* 10 pages, 7 figures 

  Access Paper or Ask Questions

One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations


Jun 02, 2021
Henry Kvinge, Scott Howland, Nico Courts, Lauren A. Phillips, John Buckheit, Zachary New, Elliott Skomski, Jung H. Lee, Sandeep Tiwari, Jessica Hibler, Courtney D. Corley, Nathan O. Hodas

* 15 pages 

  Access Paper or Ask Questions

Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning


Sep 23, 2020
Henry Kvinge, Zachary New, Nico Courts, Jung H. Lee, Lauren A. Phillips, Courtney D. Corley, Aaron Tuor, Andrew Avila, Nathan O. Hodas

* 17 pages 

  Access Paper or Ask Questions

The Outer Product Structure of Neural Network Derivatives


Oct 09, 2018
Craig Bakker, Michael J. Henry, Nathan O. Hodas


  Access Paper or Ask Questions

Doing the impossible: Why neural networks can be trained at all


May 28, 2018
Nathan O. Hodas, Panos Stinis

* The material is based on a poster from the 15th Neural Computation and Psychology Workshop "Contemporary Neural Network Models: Machine Learning, Artificial Intelligence, and Cognition" August 8-9, 2016, Drexel University, Philadelphia, PA, USA 

  Access Paper or Ask Questions

How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions?


Mar 18, 2018
Garrett B. Goh, Charles Siegel, Abhinav Vishnu, Nathan O. Hodas, Nathan Baker

* In Proceedings of 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) 

  Access Paper or Ask Questions

SMILES2Vec: An Interpretable General-Purpose Deep Neural Network for Predicting Chemical Properties


Mar 18, 2018
Garrett B. Goh, Nathan O. Hodas, Charles Siegel, Abhinav Vishnu

* Submitted to SIGKDD 2018 

  Access Paper or Ask Questions

Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction


Mar 18, 2018
Garrett B. Goh, Charles Siegel, Abhinav Vishnu, Nathan O. Hodas

* Submitted to SIGKDD 2018 

  Access Paper or Ask Questions

Few-Shot Learning with Metric-Agnostic Conditional Embeddings


Feb 12, 2018
Nathan Hilliard, Lawrence Phillips, Scott Howland, Artëm Yankov, Courtney D. Corley, Nathan O. Hodas


  Access Paper or Ask Questions

Dynamic Input Structure and Network Assembly for Few-Shot Learning


Aug 22, 2017
Nathan Hilliard, Nathan O. Hodas, Courtney D. Corley


  Access Paper or Ask Questions

Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models


Jun 20, 2017
Garrett B. Goh, Charles Siegel, Abhinav Vishnu, Nathan O. Hodas, Nathan Baker

* Submitted to a chemistry peer-reviewed journal 

  Access Paper or Ask Questions

Deep Learning for Computational Chemistry


Jan 17, 2017
Garrett B. Goh, Nathan O. Hodas, Abhinav Vishnu


  Access Paper or Ask Questions

Mutual information for fitting deep nonlinear models


Dec 17, 2016
Jacob S. Hunter, Nathan O. Hodas


  Access Paper or Ask Questions

Beyond Fine Tuning: A Modular Approach to Learning on Small Data


Nov 06, 2016
Ark Anderson, Kyle Shaffer, Artem Yankov, Court D. Corley, Nathan O. Hodas


  Access Paper or Ask Questions