Reposted by David Dalmau
Dalmau et al. automate non-linear ML workflows for tiny chemical datasets. With robust hyperparameter tuning and an overfitting-aware metric, random forests, gradient boosting, and NNs rival or surpass linear regression, expanding chemists’ low-data modeling toolbox. pubs.rsc.org/en/Content/A...
pubs.rsc.org
Machine learning workflows beyond linear models in low-data regimes
Data-driven methodologies are transforming chemical research by providing chemists with digital tools that accelerate discovery and promote sustainability. In this context, non-linear machine learning...
