Just-So Stories for AI - Explaining Black-Box Predictions

Just-So Stories for AI - Explaining Black-Box Predictions

Strange Loop Conference via YouTube Direct link

Models

5 of 29

5 of 29

Models

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Just-So Stories for AI - Explaining Black-Box Predictions

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction
  2. 2 Outline
  3. 3 Stripe
  4. 4 Rules
  5. 5 Models
  6. 6 Decision Trees
  7. 7 Random Forest
  8. 8 Explanations
  9. 9 Intuition
  10. 10 Structure
  11. 11 Algorithm
  12. 12 Explanation
  13. 13 Elephant Trunk
  14. 14 Observation
  15. 15 Lime
  16. 16 AI Rationalisation
  17. 17 Frogger
  18. 18 Methow submodel interpretability
  19. 19 Human interpretability
  20. 20 Peter Norvig
  21. 21 Roger Sperry
  22. 22 Homo Deus
  23. 23 Algorithms
  24. 24 Explanations are harmful
  25. 25 Why explanations are important
  26. 26 Human compatible AI
  27. 27 Data protection regulation
  28. 28 Clarify our ethics
  29. 29 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.