Interpretable machine learning : a guide for making Black Box Models interpretable

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. Preface by the Author | Interpretable Machine Learning Chapter 1 Introduction | Interpretable Machine Learning 1.1 Story Time | Interpretable Machine Learning 1.2 What Is Machine Learning? | Interpretable Machine Learning 1.3 Terminology | Interpretable Machine Learning Chapter 2 Interpretability | Interpretable Machine Learning 2.1 Importance of Interpretability | Interpretable Machine Learning 2.2 Taxonomy of Interpretability Methods | Interpretable Machine Learning 2.3 Scope of Interpretability | Interpretable Machine Learning 2.4 Evaluation of Interpretability | Interpretable Machine Learning 2.5 Properties of Explanations | Interpretable Machine Learning 2.6 Human-friendly Explanations | Interpretable Machine Learning Chapter 3 Datasets | Interpretable Machine Learning 3.1 Bike Rentals (Regression) | Interpretable Machine Learning 3.2 YouTube Spam Comments (Text Classification) | Interpretable Machine Learning 3.3 Risk Factors for Cervical Cancer (Classification) | Interpretable Machine Learning Chapter 4 Interpretable Models | Interpretable Machine Learning 4.1 Linear Regression | Interpretable Machine Learning 4.2 Logistic Regression | Interpretable Machine Learning 4.3 GLM, GAM and more | Interpretable Machine Learning 4.4 Decision Tree | Interpretable Machine Learning 4.5 Decision Rules | Interpretable Machine Learning 4.6 RuleFit | Interpretable Machine Learning 4.7 Other Interpretable Models | Interpretable Machine Learning Chapter 5 Model-Agnostic Methods | Interpretable Machine Learning 5.1 Partial Dependence Plot (PDP) | Interpretable Machine Learning 5.2 Individual Conditional Expectation (ICE) | Interpretable Machine Learning 5.3 Accumulated Local Effects (ALE) Plot | Interpretable Machine Learning 5.4 Feature Interaction | Interpretable Machine Learning 5.5 Permutation Feature Importance | Interpretable Machine Learning 5.6 Global Surrogate | Interpretable Machine Learning 5.7 Local Surrogate (LIME) | Interpretable Machine Learning 5.8 Scoped Rules (Anchors) | Interpretable Machine Learning 5.9 Shapley Values | Interpretable Machine Learning 5.10 SHAP (SHapley Additive exPlanations) | Interpretable Machine Learning Chapter 6 Example-Based Explanations | Interpretable Machine Learning 6.1 Counterfactual Explanations | Interpretable Machine Learning 6.2 Adversarial Examples | Interpretable Machine Learning 6.3 Prototypes and Criticisms | Interpretable Machine Learning 6.4 Influential Instances | Interpretable Machine Learning Chapter 7 Neural Network Interpretation | Interpretable Machine Learning 7.1 Learned Features | Interpretable Machine Learning 7.2 Pixel Attribution (Saliency Maps) | Interpretable Machine Learning Chapter 8 A Look into the Crystal Ball | Interpretable Machine Learning 8.1 The Future of Machine Learning | Interpretable Machine Learning 8.2 The Future of Interpretability | Interpretable Machine Learning Chapter 9 Contribute to the Book | Interpretable Machine Learning Chapter 10 Citing this Book | Interpretable Machine Learning Chapter 11 Translations | Interpretable Machine Learning Chapter 12 Acknowledgements | Interpretable Machine Learning References | Interpretable Machine Learning R Packages Used for Examples | Interpretable Machine Learning