How Can I Explain This to You? An Empirical Study of Deep Neural Net Explanation Methods - Spring 2021

How Can I Explain This to You? An Empirical Study of Deep Neural Net Explanation Methods - Spring 2021

UCF CRCV via YouTube Direct link

Privacy Risks

23 of 25

23 of 25

Privacy Risks

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

How Can I Explain This to You? An Empirical Study of Deep Neural Net Explanation Methods - Spring 2021

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

  1. 1 Intro
  2. 2 Outline
  3. 3 Motivation
  4. 4 Introduction
  5. 5 Key Contributions
  6. 6 Study Details
  7. 7 Unifying Visual Explanation Methods Across Input Domains
  8. 8 Saliency map
  9. 9 Scoped Rules (Anchors)
  10. 10 SHAPISHapley Additive exPlanations
  11. 11 A Unified Representation of Visual Explanation Frameworks
  12. 12 Superimposition Based Explanation Methods
  13. 13 Training Data Based Explanation Methods
  14. 14 Study Methodology
  15. 15 Validating Responses
  16. 16 Tasks & Datasets
  17. 17 Models and Explanations
  18. 18 Configuring and Optimizing Explanation Methods
  19. 19 Results
  20. 20 Usability and Stability of Explanations
  21. 21 Idealized vs Actualized Explanations - Superimposition Methods
  22. 22 Explanation-by-Example
  23. 23 Privacy Risks
  24. 24 Conclusion
  25. 25 Against

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.