10-744 Machine Learning for Science

12 units, Carnegie Mellon University

This course will cover important topics that surround the use of Machine Learning to make scientific inferences. This includes methodological domains such as robustness and reproducibility, statistical testing, model interpretability, post-selection inference, tradeoff of simplicity and predictivity, learning from scratch vs. implementing domain knowledge, etc. We will evaluate these topics in general as well as applied to specific scientific fields. We will also interact with a wide array of scientists from different disciplines on campus to understand how Machine Learning is currently applied in the domain of science.

Prerequisites: 07-280 (min C) or 10-301 (min C) or 10-601 (min C) or 10-715 (min C) or 10-701 (min C) or 10-315 (min C)

Offered: Fall 2025

Courseweave needs JavaScript to show sections, workloads and planning tools.