Embedded Files
Week 2: Sept. 4
Introduction to Classic Explanation Methods
Week 3: Sept. 11
Feature Attribution Explanation: Attention-based Methods
Week 4: Sept. 18
Hierarchical Explanation
Week 5: Sept. 25
Interpretable and Rationalized Models
Week 6: Oct. 2
Natural Language Explanation
Week 7: Oct. 9
Prompting for LLM Explainability
Week 8: Oct. 16
Human-Centered Explanation
Week 9: Oct. 23
Mechanistic Interpretability: Neurons, Features
Week 10: Oct. 30
Mechanistic Interpretability: Probing, Patching
Week 11: Nov. 6
Explanation Evaluation
Week 12: Nov. 13
Usability of XAI: Editing
Week 13: Nov. 20
Usability of XAI: Safety
Week 14: Nov. 27
THANKSGIVING RECESS
Week 15: Dec. 4
Final Project Presentation
Page updated
Report abuse