CSE574: Explainable Artificial Intelligence
Catalog Description: Approaches to enhancing the interpretability and transparency of complex machine learning models, encompassing both inherently interpretable models and post hoc explanation methods. Explores a spectrum of techniques, ranging from feature attributions and their evaluation metrics to counterfactual explanations, concept-based explanations, instance explanations, and collaboration between humans and artificial intelligence.
Prerequisities: (none listed) Credits: 4.0Portions of the CSE574 web may be reprinted or adapted for academic nonprofit purposes, providing the source is accurately quoted and duly credited. The CSE574 Web: © 1993-2025, Department of Computer Science and Engineering, University of Washington. Administrative information on CSE574 (authentication required).