Completed
Compiling classifiers into class formulas from decision trees, random forests, Bayesian networks, and Binary neural networks
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Logic for Explainable AI - Tutorial
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction
- 2 From numeric to symbolic classifiers
- 3 Representing classifiers using tractable circuits
- 4 Representing classifiers using class formulas
- 5 Discrete logic vs Boolean logic
- 6 The sufficient reasons for decisions: why a decision was made? aka abductive explanations, PI-explanations
- 7 The complete reasons for decisions: instance abstraction
- 8 The necessary reasons for decisions: how to change a decision? aka contrastive explanations, counterfactual explanations
- 9 Terminology: PI-explanations, abductive explanations, contrastive explanations, counterfactual explanations
- 10 A logical operator for computing instance abstractions complete reasons
- 11 The first theory of explanation: A summary
- 12 Beyond simple explanations: A key insight
- 13 The general reasons for decisions: instance abstraction
- 14 Complete vs general reasons two notions of instance abstraction
- 15 The general sufficient and general necessary reasons for decisions
- 16 The second theory of explanation: A summary
- 17 Targeting a new decision
- 18 Selection semantics of complete and general reasons instance abstractions
- 19 Compiling classifiers into class formulas from decision trees, random forests, Bayesian networks, and Binary neural networks
- 20 Conclusion
