This part will introduce you to the world of interpretable AI. In chapter 1, you will learn about different types of AI systems, interpretability and its importance, white-box and black-box models, and how to build interpretable AI systems.
In chapter 2, you will learn about characteristics that make white-box models inherently transparent and black-box models inherently opaque. You’ll learn how to interpret simple white-box models, such as linear regression and decision trees and then switch gears to focus on generalized additive models (GAMs). You’ll also learn about the properties that give GAMs high predictive power and how to interpret them. GAMs have very high predictive power and are highly interpretable too, so you get more bang for your buck by using GAMs.