Introduction: Interpreting Black Box Transformer Models
Get an overview of what we will cover in this chapter.
We'll cover the following
Million-to billion-parameter transformer models seem like huge opaque boxes that nobody can interpret. As a result, many developers and users have sometimes been discouraged when dealing with these mind-blowing models. However, recent research has begun to solve the problem with innovative, cutting-edge tools.
Chapter Overview
It is beyond the scope of this course to describe all of the explainable AI methods and algorithms. So instead, this chapter will focus on ready-to-use visual interfaces that provide insights for transformer model developers and users.
The chapter begins by importing and running BertViz by Jesse Vig. Jesse did quite an excellent job of building a visual interface that shows the activity in the attention heads of a BERT transformer model. BertViz interacts with the BERT models and provides a well-designed interactive interface.
Get hands-on with 1200+ tech skills courses.