Chemically-informed data-driven optimization (ChIDDO): leveraging physical models and Bayesian learning to accelerate chemical research
Daniel Frey, Ju Hee Shin, Christopher Musco, Miguel A. Modestino
Abstract
A method combining information from both experiments and physics-based models is used to improve experimental Bayesian optimization.
Topics & Concepts
Bayesian optimizationBayesian probabilityComputer scienceMachine learningBayesian inferenceExperimental dataArtificial intelligenceData scienceMathematicsStatisticsMachine Learning in Materials ScienceComputational Drug Discovery MethodsProcess Optimization and Integration