Characterizing Uncertainty in Machine Learning for Chemistry.

ABSTRACT: Characterizing uncertainty in machine learning models has recently gained interest in the context of machine learning reliability, robustness, safety, and active learning. Here, we separate the total uncertainty into contributions from noise in the data (aleatoric) and shortcomings of the model (epistemic), further dividing epistemic uncertainty into model bias and variance contributions. We systematically address the influence of noise, model bias, and model variance in the context of chemical property predictions, where the diverse nature of target properties and the vast chemical chemical space give rise to many different distinct sources of prediction error. We demonstrate that different sources of error can each be significant in different contexts and must be individually addressed d

SUBMITTER: Heid E 

PROVIDER: S-EPMC10336963 | biostudies-literature | 2023 Jul

REPOSITORIES: biostudies-literature