DOE OSTI · 1924099
Quantifying the performance of machine learning models in materials discovery
Abstract
In this work, we simulate a sequential learning (SL)-guided materials discovery process and demonstrate a decoupling between traditional model error metrics and model performance in guiding materials discoveries.
Keep this discovery
Explore connections, maps & timelines
Borg, Christopher K. H., Muckley, Eric S., Nyby, Clara, Saal, James E., Ward, Logan, Mehta, Apurva, Meredig, Bryce. 2023-04-11. Quantifying the performance of machine learning models in materials discovery. https://doi.org/10.1039/d2dd00113f
Cite the original work for its findings. Save a collection to share your selection of sources.