Delta Keyword Transformer: Bringing Transformers to the Edge Through Dynamically Pruned Multi-Head Self-Attention

Delta Keyword Transformer: Bringing Transformers to the Edge Through Dynamically Pruned Multi-Head Self-Attention

tinyML via YouTube Direct link

Delta for softmax

9 of 13

9 of 13

Delta for softmax

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Delta Keyword Transformer: Bringing Transformers to the Edge Through Dynamically Pruned Multi-Head Self-Attention

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

  1. 1 Intro
  2. 2 Overview Transformers
  3. 3 Previous work
  4. 4 Keyword Transformer (KWT)
  5. 5 KWT-Model analysis
  6. 6 Delta algorithm
  7. 7 Delta-regular matrix multiplication
  8. 8 Delta-delta matrix multiplication
  9. 9 Delta for softmax
  10. 10 Delta Keyword Transformer
  11. 11 Results 1
  12. 12 Conclusion
  13. 13 Premier: EDGE IMPULSE

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.