Explainable AI for Practitioners: Designing and Implementing Explainable ML Solutions

by Michael Munn, David Pitman

Most intermediate-level machine learning books focus on how to optimize models by increasing accuracy or decreasing prediction error. But this approach often overlooks the importance of understanding why and how your ML model makes the predictions that it does. Explainability methods provide an essential toolkit for better understanding model behavior, and this practical guide brings together best-in-class techniques for model explainability. Experienced machine learning engineers and data scientists will learn hands-on how these techniques work so that you'll be able to apply these tools more easily in your daily workflow. This essential book

Genres: Artificial Intelligence

276 pages, Paperback

Published December 6, 2022

Reviews

[Laura Uzcategui · Rating 5 out of 5]

Great book on Explainable AI from the technical point of view is a good reference that will allow you to learn more about techniques for performing Explainability when implementing ML models and algorithms.

The authors go from basics to most profound levels by showing you examples and real use cases of what it is used in the industry and not only that but raise awareness that this is a new area and it’s full of opportunities for exploring, researching and implementing new techniques around the area, always keeping in mind that one have to adjust the levels depending of the audience who is receiving the explanations itself.

I truly enjoyed reading this book and learnt a lot by the content exposed in it.