Interpretable Machine Learning

Host University

George Mason University

Semester

Fall 2024

Course Number

AIT 636 DL1

Credits

3

Discipline

Computer Engineering

Instructor

Hashemi, Mahdi (mhashem2@gmu.edu)

Times and Days

Asynchronous

Course Information

One of the most common tasks performed by data scientists and data analysts is prediction and machine learning. Machine learning combines advanced topics in statistics, probabilities, linear algebra, and calculus to design mathematical models that learn from data or experience to solve new problems. Computers usually do not explain their predictions which is a barrier to the adoption of machine learning. This course focuses on making the decisions from algorithms more understandable for humans. In other words, making machine learning models and their decisions interpretable. This course covers simple, interpretable models such as decision trees, decision rules and linear regression. It also covers general model-agnostic methods for interpreting black box models like feature importance and model settings. Offered by Info Sciences & Technology. May not be repeated for credit.