Assessing the Frontier: Active Learning, Model Accuracy, and Multi-objective Materials Discovery and Optimization

no code implementations • 6 Nov 2019 • Zachary del Rosario, Matthias Rupp, Yoolhee Kim, Erin Antono, Julia Ling

Discovering novel materials can be greatly accelerated by iterative machine learning-informed proposal of candidates---active learning.

Active Learning BIG-bench Machine Learning

Data-driven dimensional analysis: algorithms for unique and relevant dimensionless groups

no code implementations • 4 Aug 2017 • Paul G. Constantine, Zachary del Rosario, Gianluca Iaccarino

We derive the algorithms by combining classical semi-empirical modeling with active subspaces, which---given a probability density on the independent variables---yield unique and relevant dimensionless groups.

Numerical Analysis Methodology