DSC 270Interpretability and Explainability in Machine Learning
This course will cover advances in interpretable and explainable machine learning. Topics include modern methods to learn simple, transparent models (e.g., rule lists, decision trees, sparse linear models); methods for post-hoc explainability (e.g., SHAP, LIME, saliency maps, prototype-generation methods); and overarching concepts in the interpretation, description, explanation of machine learning (e.g., model multiplicity, cognitive biases, user studies).
Prerequisites
From the catalog: “DSC 240. Students should be comfortable reading research papers with a critical perspective; have prior course work in machine learning (e.g., DSC 240); and have some interest in interpretability and explainability for your research or career. Restricted to major codes DS75 and DS76.”