Interpretable Machine Learning
This book is 98% complete
Last updated on 2019-01-22
About the Book
"Book on interpretability of ML models, such an important topic often neglected" - @prdeepakbabu
Machine learning has great potential for improving products, processes and research. But computers usually don’t explain their predictions, which is a barrier to the adoption of machine learning. 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. The later chapters focus on general model-agnostic tools for interpreting black box models and explaining individual predictions. In an ideal future, machines will be able to explain their decisions and the algorithmic age we move toward will be as human as possible.
The book focuses on machine learning models for tabular data (also called relational or structured data) and less on computer vision and natural language processing tasks. This book is recommended for machine learning practitioners, data scientists, statisticians, and anyone else interested in making machine learning more interpretable.
A free HTML version of the book can be found at: https://christophm.github.io/interpretable-ml-book/
- Story Time
- What Is Machine Learning?
- Importance of Interpretability
- Taxonomy of Interpretability Methods
- Scope of Interpretability
- Evaluation of Interpretability
- Properties of Explanations
- Human-friendly Explanations
- Bike Rentals (Regression)
- YouTube Spam Comments (Text Classification)
- Risk Factors for Cervical Cancer (Classification)
- Linear Regression
- Logistic Regression
- GLM, GAM and more
- Decision Tree
- Decision Rules
- Other Interpretable Models
- Partial Dependence Plot (PDP)
- Individual Conditional Expectation (ICE)
- Accumulated Local Effects (ALE) Plot
- Feature Interaction
- Feature Importance
- Global Surrogate
- Local Surrogate (LIME)
- Shapley Values
- Counterfactual Explanations
- Adversarial Examples
- Prototypes and Criticisms
- Influential Instances
A Look into the Crystal Ball
- The Future of Machine Learning
- The Future of Interpretability
- Contribute to the Book
- Citing this Book
The Leanpub 45-day 100% Happiness Guarantee
Within 45 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
See full terms...