Machine Learning for Catalysis

This lecture covers the application of machine learning in catalysis, focusing on the use of ML models to predict chemical properties, molecular representations, and catalyst performance. Topics include the Coulomb Matrix, Bag of Bonds, and Spectrum of London and Axilrod-Teller-Muto representations, as well as Kernel Ridge Regression. The lecture explores the systematic screening of molecular catalysts, the ML exploration of catalyst landscapes, and the use of ML models for cross-coupling reactions. Various ML models are discussed, such as Support Vector Machines and Neural Networks, in predicting selective catalysts for chemical reactions.