Interpretable Machine Learning in Python

This book will help you work consciously and effectively with machine learning models. It provides an introduction to the interpretation of machine learning: the importance of the topic, its key concepts and issues are revealed. Interpretation methods are considered: model-agnostic, anchor, and counterfactual, for multivariate forecasting, as well as the visualization of convolutional neural networks. Issues of tuning for interpretability are revealed: feature selection and construction, mitigating systematic bias, causal inference, monotonic constraints, model tuning, and robustness to antagonism. The prospects for the development of interpretable machine learning models are shown. Each chapter of the book includes detailed examples of source code in Python.
A website archive with color illustrations is available from the publisher.
For programmers in the field of machine learning.