This course surveys the application of data science (DS) and machine learning (ML) to problems arising in engineering and the sciences. While DS and ML have profoundly affected domains such as image understanding and natural language processing, ML has seen comparatively less impact in chemistry, physics, chemical engineering, electrical engineering, and many other important application domains. Topics covered will include predictive modeling, feature engineering, and model assessment, with a particular focus on the small-data limit. We will analyze and apply algorithms with wide applicability in engineering and sciences including classic techniques such as multiple linear regression and random forests, and state-of-the-art techniques such as deep neural networks.
The intention is for the class to be accessible to a wide audience in disciplines outside of Computer Science and Data Science, though some basic background topics such as statistics or linear algebra, and the ability to learn Python programming at a basic level would be helpful.