Thinking Like Transformers

Gail Weiss
Gail Weiss
Eran Yahav
Eran Yahav
Cited by: 0|Views4

Abstract:

What is the computational model behind a transformer? Where recurrent neural networks have direct parallels in finite state machines, allowing clear discussion and thought around architecture variants or trained models, transformers have no such familiar parallel. In this paper we aim to change that, proposing a computational model for th...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments