Understanding, Interpreting and Designing Neural Network Models Through Tensor Representations

Understanding, Interpreting and Designing Neural Network Models Through Tensor Representations

Institute for Pure & Applied Mathematics (IPAM) via YouTube Direct link

Results

26 of 27

26 of 27

Results

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Understanding, Interpreting and Designing Neural Network Models Through Tensor Representations

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

  1. 1 Introduction
  2. 2 Challenges in Neural Networks
  3. 3 Robustness of Neural Networks
  4. 4 Outline
  5. 5 Conceptual Challenge
  6. 6 Computational Challenge
  7. 7 Goal
  8. 8 Background Knowledge
  9. 9 Compression Techniques
  10. 10 Compression Methods
  11. 11 CP Layer
  12. 12 Low Rankedness
  13. 13 Reshaping
  14. 14 Generalization Error Bound
  15. 15 Performance
  16. 16 Evaluation
  17. 17 Interpreting transformers
  18. 18 Operations in tensor diagrams
  19. 19 Benefits of tensor diagrams
  20. 20 Single Hat SelfAttention
  21. 21 Multi Hat SelfAttention
  22. 22 Multi Hat Modes
  23. 23 Recap
  24. 24 Improved expressive power
  25. 25 Tensor representation for robust learning
  26. 26 Results
  27. 27 Summary

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.