Embedded Files
Week 3: Sept. 12
Feature Attribution Explanation: Attention-based Methods
Week 4: Sept. 19
Multi-Level Explanation
Week 5: Sept. 26
Interpretable and Rationalized Models
Week 6: Oct. 3
Data Attribution
Week 7: Oct. 10
Natural Language Explanation
Week 8: Oct. 17
Prompting-Based Techniques for Explainability
Week 9: Oct. 24
Human-Centered Explanation
Week 10: Oct. 31
Mechanistic Interpretability: Neurons, Circuits, Concepts
Week 11: Nov. 7
Mechanistic Interpretability: Probing, Patching
Week 12: Nov. 14
Explanation Evaluation
Week 13: Nov. 21
Explanation Utility
Week 14: Nov. 28
THANKSGIVING RECESS
Week 15: Dec. 5
Final Project Presentation
Page updated
Google Sites
Report abuse