Completed
Introduction
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Blowing Up Transformer Decoder Architecture
Automatically move to the next video in the Classroom when playback concludes
- 1 Introduction
- 2 What is the Encoder doing?
- 3 Text Processing
- 4 Why are we batching data?
- 5 Position Encoding
- 6 Query, Key and Value Tensors
- 7 Masked Multi Head Self Attention
- 8 Residual Connections
- 9 Multi Head Cross Attention
- 10 Finishing up the Decoder Layer
- 11 Training the Transformer
- 12 Inference for the Transformer