You're reading from Interpretable Machine Learning with Python Build explainable, fair, and robust high-performance models with hands-on, real-world examples

Product type Paperback

Published in Oct 2023

Publisher Packt

ISBN-13 9781803235424

Length 606 pages

Edition 2nd Edition

Languages

Python

Tools

BERT

Concepts

Machine Learning

Author (1):

Serg Masís

View More author details

Table of Contents (17) Chapters

Preface

1. Interpretation, Interpretability, and Explainability; and Why Does It All Matter?

2. Key Concepts of Interpretability FREE CHAPTER

3. Interpretation Challenges

4. Global Model-Agnostic Interpretation Methods

5. Local Model-Agnostic Interpretation Methods

6. Anchors and Counterfactual Explanations

7. Visualizing Convolutional Neural Networks

8. Interpreting NLP Transformers

9. Interpretation Methods for Multivariate Forecasting and Sensitivity Analysis

10. Feature Selection and Engineering for Interpretability

11. Bias Mitigation and Causal Inference Methods

12. Monotonic Constraints and Model Tuning for Interpretability

13. Adversarial Robustness

14. What’s Next for Machine Learning Interpretability?

15. Other Books You May Enjoy

16. Index

The mission

In the United States, for the last two decades, private companies and nonprofits have developed criminal Risk Assessment Instruments/Tools (RAIs), most of which employ statistical models. As many states can no longer afford their large prison populations, these methods have increased in popularity, guiding judges and parole boards through every step of the prison system.

These are high-impact decisions that can determine if a person is released from prison. Can we afford for these decisions to be wrong? Can we accept the recommendations from these systems without understanding why they were made? Worst of all, we don’t exactly know how an assessment was made. The risk is usually calculated with a white-box model, but, in practice, a black-box model is used because it is proprietary. Predictive performance is also relatively low, with median AUC scores for a sample of nine tools ranging between 0.57 and 0.74 according to the paper Performance of Recidivism Risk...

The rest of the chapter is locked

You're reading from Interpretable Machine Learning with Python Build explainable, fair, and robust high-performance models with hands-on, real-world examples

Table of Contents (17) Chapters

The mission

Authors (1)

Personalised recommendations for you

You're reading from Interpretable Machine Learning with Python Build explainable, fair, and robust high-performance models with hands-on, real-world examples

Table of Contents (17) Chapters

The mission

Unlock this book and the full library FREE for 7 days

Authors (1)

Personalised recommendations for you