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