Completed
Masked Self-Attention, an Autoregressive method
Class Central Classrooms beta
YouTube playlists curated by Class Central.
Classroom Contents
Decoder-Only Transformers, ChatGPT's Specific Transformer, Clearly Explained
Automatically move to the next video in the Classroom when playback concludes
- 1 Transformers are taking over AI right now, and quite possibly their most famous use is in ChatGPT. ChatGPT uses a specific type of Transformer called a Decoder-Only Transformer, and this StatQuest sh…
- 2 Awesome song and introduction
- 3 Word Embedding
- 4 Position Encoding
- 5 Masked Self-Attention, an Autoregressive method
- 6 Residual Connections
- 7 Generating the next word in the prompt
- 8 Review of encoding and generating the prompt
- 9 Generating the output, Part 1
- 10 Masked Self-Attention while generating the output
- 11 Generating the output, Part 2
- 12 Normal Transformers vs Decoder-Only Transformers
