David Dalmau

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...

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...

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...

👉🏻 Are linear models the only/best choice for small databases in machine learning? Check out our work to implement nonlinear models in low-data regimes using ROBERT v2! @chemicalscience.rsc.org

📝 Read: pubs.rsc.org/en/content/a... |
🔧Install: robert.readthedocs.io/en/latest/