Logic for Explainable AI - Tutorial

Logic for Explainable AI - Tutorial

UCLA Automated Reasoning Group via YouTube Direct link

Conclusion

20 of 20

20 of 20

Conclusion

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

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.