DESCRIPTION

Introduction to the emerging field of Explainable Artificial Intelligence (XAI) from the perspectives of a developer and end-user. Students will gain hands-on experience with some of the most commonly used explainability techniques and algorithms.

COURSE NOTES

This course provides an Introduction to Explainable AI (XAI) through practical applications and real-world examples. Students will gain a basic proficiency in interpreting and explaining the decisions of ML and AI systems, in a transparent and understandable manner to humans. The course will cover various XAI techniques and algorithms, including rule-based models, feature importance analysis, model-agnostic approaches, and post-hoc explanations. Another primary focus will be on evaluating the performance of explainability techniques, quantifying their uncertainty, and understanding the trade-offs associated with various methods. This course is geared towards students interested in a hands-on approach to developing explanations in ML and AI Systems. Course Objectives: - Understand what Explainable AI (XAI) is, its scope, and impact on various domains - Understand Global vs Local Explainability and their applications - Identify and evaluate different XAI techniques and algorithms. - Apply XAI techniques and algorithms to analyze and explain ML model outputs. - Critically evaluate and contextualize the performance and usability of Explainer Algorithms, and identify their limitations and biases.

PREREQUISITES

Informatics 304 and 310D.

This topic also requires prior credit in I 306 Statistics for Informatics or equivalent course substitute.

RESTRICTIONS

Registration prioritized for undergraduate Informatics majors through registration period 1, with access being extended to Informatics minors beginning in period 2. Outside students will be permitted to join our waitlists beginning with period 3.