Interpretable Machine Learning

A Guide for Making Black Box Models Explainable

by Christoph Molnar

DescriptionTable of ContentsDetailsHashtagsReport an issue

Book Description

This book is about making machine learning models and their decisions interpretable. After exploring the concepts of interpretability, you will learn about simple, interpretable models such as decision trees, decision rules and linear regression. Later chapters focus on general model-agnostic methods for interpreting black box models like feature importance and accumulated local effects and explaining individual predictions with Shapley values and LIME. All interpretation methods are explained in depth and discussed critically. How do they work under the hood? What are their strengths and weaknesses? How can their outputs be interpreted? This book will enable you to select and correctly apply the interpretation method that is most suitable for your machine learning project.

This open book is licensed under a Creative Commons License (CC BY-NC-SA). You can download Interpretable Machine Learning ebook for free in PDF format (8.7 MB).

Table of Contents

 
Introduction
 
Interpretability
 
Datasets
 
Interpretable Models
 
Model-Agnostic Methods
 
Example-Based Explanations
 
A Look into the Crystal Ball
 

Book Details

Subject
Computer Science
Publisher
Leanpub
Published
2020
Pages
312
Edition
1
Language
English
ISBN13 Digital
9780244768522
ISBN10 Digital
0244768528
PDF Size
8.7 MB
License
CC BY-NC-SA

Related Books