Completed
It's hard to opt-out
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
An Overview of Local Explainability Methods and Their Evaluation in AI
Automatically move to the next video in the Classroom when playback concludes
- 1 Announcements
- 2 It's hard to opt-out
- 3 Confidence scores
- 4 Explanations in plain English free-text / chain-of-thoughts
- 5 Input attribution gradient-based & select-then-predict
- 6 Feature interactions effective attention
- 7 Concept-based explanations TCAV
- 8 Data influence influence functions
- 9 Contrastive explanations contrastive editing
- 10 Explainability as a dialog
- 11 Taxonomy of evaluation of explanations
- 12 Simulatability
- 13 Why are application-grounded evals of explanations scarce in NLP?
- 14 Application-grounded evaluations
- 15 Trust in AI
