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