Project 2 —— Machine Learning in Chemistry

Abstract

—The dramatic development of machine learning has led to its widespread use in many fields, including the field of chemistry. A widely used molecular representation in quantum chemistry, physics-based molecular representation, suffers from the problem of redundant vectors with a large number of features. In this project, seven feature selection algorithms are applied to reduce the dimensionality of a molecular representation dataset with a huge number of features, and the prediction accuracy is compared.