A Modern and Scalable Approach to Responsible AI

Audit, Assess, and Evaluate AI Systems

Understanding machine learning (ML) systems is a critical task for data scientists and non-technical profiles alike as organizations aim to integrate AI applications on an enterprise-wide level.

In this ebook, we explore practices to identify cutting-edge and responsible strategies for managing high-impact AI systems and work to understand the concepts and techniques of model interpretability and explainability.

2021 OReilly Responsible AI Mini 3D Cover

Get the O’Reilly Ebook

Understanding the Task at Hand

Early Release Chapters 1-5 Feature:

  • A precis of all of that model governance encompasses today and the best execution methods for practitioners
  • Insight into the best practices for debugging ML systems for safety and performance
  • An overview of security for ML to effectively audit for any potential vulnerabilities
  • An introduction to interpretability and explainability ideas, with a discussion of applying interpretable models and post-hoc explanations
  • An XGBoost explanation, technical concepts review, and an example credit underwriting problem