A Review of Compression Methods for Deep Convolutional Neural Networks

A Review of Compression Methods for Deep Convolutional Neural Networks

tinyML via YouTube Direct link

Introduction

1 of 27

1 of 27

Introduction

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

A Review of Compression Methods for Deep Convolutional Neural Networks

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

  1. 1 Introduction
  2. 2 Outline
  3. 3 Deep Learning
  4. 4 Problems with Deep Learning
  5. 5 Data Centers and Deep Learning
  6. 6 Layers
  7. 7 Data Sets
  8. 8 Questions
  9. 9 Architectures
  10. 10 Number of operations
  11. 11 Convolutional layers
  12. 12 Comparison of architectures
  13. 13 Comparing architectures
  14. 14 Retraining feature maps
  15. 15 Quantizing parameters
  16. 16 Quantization experiment
  17. 17 Flops rate
  18. 18 Compensation during training
  19. 19 Quantization during training
  20. 20 Quantization for precision
  21. 21 Results
  22. 22 Shift Attention Layers
  23. 23 Clustering weights
  24. 24 Energy consumption
  25. 25 Summary
  26. 26 Conclusion
  27. 27 Questions and Recap

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.