TransformerFAM and BSWA: Understanding Feedback Attention Memory and Block Sliding Window Attention

TransformerFAM and BSWA: Understanding Feedback Attention Memory and Block Sliding Window Attention

Discover AI via YouTube Direct link

Time series visualization of new FAM and BSWA

8 of 9

8 of 9

Time series visualization of new FAM and BSWA

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

TransformerFAM and BSWA: Understanding Feedback Attention Memory and Block Sliding Window Attention

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

  1. 1 3 videos on infinity context length
  2. 2 Visualization of new transformerFAM
  3. 3 Pseudocode for two new transformer
  4. 4 Basics of Attention calculations
  5. 5 TransformerBSWA - Block Sliding Window Attention
  6. 6 TransformerFAM - Feedback Attention Memory
  7. 7 Symmetries in operational feedback code
  8. 8 Time series visualization of new FAM and BSWA
  9. 9 Outlook on Reasoning w/ TransformerFAM

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.