Interpretable Machine Learning, Second Edition
If you’re looking for a book that will help you make machine learning models explainable, look no further than Interpretable Machine Learning.
This book provides a clear and concise explanation of the methods and mathematics behind the most important approaches to making machine learning models intepretable.
You’ll learn about:
- Inherently interpretable models
- Methods that can make any machine model interpretable, such as SHAP, LIME and permutation feature importance.
- Interpretation methods specific to deep neural networks
- Why interpretability is important and what’s behind this concept
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. Reading the book is recommended for machine learning practitioners, data scientists, statisticians, and anyone interested in making machine learning models interpretable.Homepage