Computer Science
CS 573 - Interpretable Machine Learning
Description: This course introduces students to interpretable machine learning algorithms, which can be used to make accurate predictions from big data sets, while being interpretable in terms of what properties of the data are most important or relevant for making the prediction. Topics include sparse linear models (greedy selection and L1 regularization), decision trees, nearest neighbors, and model-agnostic methods which can be used to interpret predictions of any learning algorithm (such as neural networks). Letter grade only.
Units:
3
No sections currently offered.
Requirement Designation:
Prerequisite: CS 570 and Computer Science MS Milestone