Book Image

Responsible AI in the Enterprise

By : Adnan Masood, Heather Dawe
5 (1)
Book Image

Responsible AI in the Enterprise

5 (1)
By: Adnan Masood, Heather Dawe

Overview of this book

Responsible AI in the Enterprise is a comprehensive guide to implementing ethical, transparent, and compliant AI systems in an organization. With a focus on understanding key concepts of machine learning models, this book equips you with techniques and algorithms to tackle complex issues such as bias, fairness, and model governance. Throughout the book, you’ll gain an understanding of FairLearn and InterpretML, along with Google What-If Tool, ML Fairness Gym, IBM AI 360 Fairness tool, and Aequitas. You’ll uncover various aspects of responsible AI, including model interpretability, monitoring and management of model drift, and compliance recommendations. You’ll gain practical insights into using AI governance tools to ensure fairness, bias mitigation, explainability, privacy compliance, and privacy in an enterprise setting. Additionally, you’ll explore interpretability toolkits and fairness measures offered by major cloud AI providers like IBM, Amazon, Google, and Microsoft, while discovering how to use FairLearn for fairness assessment and bias mitigation. You’ll also learn to build explainable models using global and local feature summary, local surrogate model, Shapley values, anchors, and counterfactual explanations. By the end of this book, you’ll be well-equipped with tools and techniques to create transparent and accountable machine learning models.
Table of Contents (16 chapters)
Part 1: Bigot in the Machine – A Primer
Part 2: Enterprise Risk Observability Model Governance
Part 3: Explainable AI in Action

Taxonomy of ML explainability methods

A taxonomy is a system for classifying things: the benefit of building a taxonomy is that it helps us to understand and organize information in a useful manner. Due to the vast amount of research interest in the area of ML explainability, you will encounter different taxonomies around ML interpretability methods, as well as a variety of terms. Let’s get some of the fundamental terms explained before moving forward.

So far, we have established that an ML explainability method is a way of understanding how an ML model works. The benefit of different types of model interpretability methods is that they can help us to understand the behavior of complex ML models. To build upon this mental model of model interpretability, we can divide it into four distinct types.

  • Model interpretability by scope
  • Model interpretability by method
  • Model interpretability by outcome
  • Model interpretability by time of information extraction
  • ...