Machine Learning in Physics and Astronomy.

Catalog description

Machine learning is one of the fastest growing and most dynamic areas of modern physics research and data application. This course gives an introduction to the core concepts, theory and tools of machine learning as required by physicists and astronomers addressing practical data analysis tasks. Topics will include, statistics, scientific data set exploration, feature engineering, neural networks, supervised and unsupervised learning. Students will learn how to select and preprocess data, design machine learning models, evaluate model performance, and relate model inputs and outputs to the underlying physics concepts. Some prior programming experience is expected.