# Teaching Computers Chemistry

Machine Learning (ML) methods seek to use a variety of statistical tools, including neural networks, to analyze and train on massive data sets. Through both supervised and active learning methods, these ML models become increasingly accurate predictors of both computational and experimental data.

We draw on ML methods in our materials discovery research, seeking to meet the goal of accurate quantum chemical predictions with much faster speed than conventional methods that require hours or days of calculations.

## Recent Publications:

## Deep learning coordinate-free quantum chemistry

Matthew K Matlock, Max Hoffman, Na Le Dang, Dakota L. Folmsbee, Luke A. Langkamp, Geoffrey R. Hutchison, Neeraj Kumar, and S. Joshua Swamidass.”Deep learning...

## Machine learning to accelerate screening for Marcus reorganization energies

Omri D. Abarbanel, Geoffrey R. Hutchison. “Machine learning to accelerate screening for Marcus reorganization energies” J. Chem. Phys. 155, 054106 (2021). D...

## Evaluation of Thermochemical Machine Learning for Potential Energy Curves and Geometry Optimization

Dakota L. Folmsbee, David R. Koes, Geoffrey R. Hutchison. “Evaluation of Thermochemical Machine Learning for Potential Energy Curves and Geometry Optimizatio...