Completed
General Approach
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Structured Quantization for Neural Network Language Model Compression
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction
- 2 Neural network vs NLP
- 3 Language model
- 4 Memory
- 5 Neural Network
- 6 Word Embedding
- 7 Neural Network Size
- 8 General Approach
- 9 Pruning
- 10 Quantization based approaches
- 11 Fixed point quantization
- 12 Product quantization
- 13 Speed recognition performance
- 14 Binarization
- 15 Embedding Matrix
- 16 Full Precision Model
- 17 Two Methods
- 18 Results
- 19 Conclusion
- 20 Question
- 21 Sponsors
