A Technique for Extreme Compression of LSTM Models

A Technique for Extreme Compression of LSTM Models

tinyML via YouTube Direct link

Intro

1 of 23

1 of 23

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

A Technique for Extreme Compression of LSTM Models

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

  1. 1 Intro
  2. 2 What is a structured matrix
  3. 3 Why arent structured matrices more widespread
  4. 4 A large NLP application
  5. 5 Vanilla Chronic Product
  6. 6 Training Curves
  7. 7 Training Techniques
  8. 8 Training Results
  9. 9 Output Feature Vectors
  10. 10 Cometrics Adaptation
  11. 11 Regularization
  12. 12 Cometric Synchronization
  13. 13 Results
  14. 14 Training data
  15. 15 Controlling sparsity
  16. 16 Compression
  17. 17 Limitations
  18. 18 Conclusion
  19. 19 Rule of Thumb
  20. 20 More than 2 matrices
  21. 21 Why the perplexity increased
  22. 22 Posttraining decomposition
  23. 23 Sponsors

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.