Completed
– The Transformer: an encoder-predictor-decoder architecture
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Self - Cross, Hard - Soft Attention and the Transformer
Automatically move to the next video in the Classroom when playback concludes
- 1 – Welcome to class
- 2 – Listening to YouTube from the terminal
- 3 – Summarising papers with @Notion
- 4 – Reading papers collaboratively
- 5 – Attention! Self / cross, hard / soft
- 6 – Use cases: set encoding!
- 7 – Self-attention
- 8 – Key-value store
- 9 – Queries, keys, and values → self-attention
- 10 – Queries, keys, and values → cross-attention
- 11 – Implementation details
- 12 – The Transformer: an encoder-predictor-decoder architecture
- 13 – The Transformer encoder
- 14 – The Transformer “decoder” which is an encoder-predictor-decoder module
- 15 – Jupyter Notebook and PyTorch implementation of a Transformer encoder
- 16 – Goodbye :
