An introduction to machine learning interpretability

by Patrick Hall, Navdeep Gill

An Applied Perspective on Fairness, Accountability, Transparency, and Explainable AI

Innovation and competition are driving analysts and data scientists toward increasingly complex predictive modeling and machine learning algorithms. This complexity makes these models accurate but also makes their predictions difficult to understand. When accuracy outpaces interpretability, human trust suffers, affecting business adoption, regulatory oversight, and model documentation.

Banking, insurance, and healthcare in particular require predictive models that are interpretable. In this ebook, Patrick Hall and Navdeep Gill from H2O.ai thoroughly introduce the idea of machine learning interpretability and examine a set of machine learning techniques, algorithms, and models to help data scientists improve the accuracy of their predictive models while maintaining interpretability.
- Learn how machine learning and predictive modeling are applied in practice
- Understand social and commercial motivations for machine learning interpretability, fairness, accountability, and transparency
- Explore the differences between linear models and more accurate machine learning models
- Get a definition of interpretability and learn about the groups leading interpretability research
- Examine a taxonomy for classifying and describing interpretable machine learning approaches
- Learn several practical techniques for data visualization, training interpretable machine learning models, and generating explanations for complex model predictions
- Explore automated approaches for testing model interpretability

Genres: Artificial Intelligence, Computer Science

33 pages, ebook

Published April 1, 2018

Reviews

[John Faucett · Rating 2 out of 5]

My opinion of this book is largely colored by my expectations going into it. I was looking for a detailed and clear explanation of topics in the subfield of machine learning interpretability (MLI) - if you are looking for this then you are in the wrong place with this book.

It starts out by giving some very cursory taxonomy descriptions of ways in which MLI techniques can be classified, for example, whether a technique is model agnostic or model specific, and then proceeds to list short half-page summaries of MLI techniques for the rest of the book. Most if not all of the methods are linked to code examples and/or papers for further exploration.

If you are looking for a list of MLI techniques with github code examples, then this book is for you. If you want an introduction to the field, this book will leave you with a lot of questions, but might have enough linked articles for you to be able to discover more on your own.

[Budi Arsana · Rating 1 out of 5]

I didn’t understand a thing reading this book. Perhaps there is prerequisites before reading this book?

[Rastko Vukasinovic · Rating 3 out of 5]

It is an introduction...

[Lucille Nguyen · Rating 3 out of 5]

It's an introduction and overview in less than 100 pages to ML interpretability. Makes a taxonomy, lists a few methods, talks more generally. Not much else to say about it.