Introduction to Transformers by UCF
Transformers are used for modeling long dependencies between input sequence elements. This presentation contains the following contents : What is Transformer?, Self-Attention, Query, Key, Value, Position encoding, Encoder-Decoder.
Author(s): Mubarak Shah
62 Pages
Transformers by University of Colorado Boulder
The topics in this presentation are as follows : Transformer overview, Self-attention, Multi-head attention , Common transformer ingredients, Pioneering transformer: machine translation.
Author(s): Danna Gurari, University of Colorado Boulder
73 Pages
