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)
1
Part 1: Bigot in the Machine – A Primer
4
Part 2: Enterprise Risk Observability Model Governance
9
Part 3: Explainable AI in Action

Getting started with fairness

The Fairlearn toolkit is an open source tool for assessing and improving the fairness of AI systems built by data scientists and developers. Fairlearn includes a visualization dashboard and algorithms for mitigating unfairness, along with required metrics. As AI and ML algorithms increasingly shape our world, it is critical that we ensure fairness in their application by using tools that can identify and mitigate bias. Fairlearn is one such library. As we dive into the use of Fairlearn, we must understand the reasons why it is important to consider the potential impact of sensitive features on your ML models, even if you are not explicitly including sensitive features in the training data.

A common misconception is “If we remove sensitive features such as a person’s race, sex, religion, sexual orientation, veteran status, and so on, shouldn’t that be enough to mitigate any bias?” The answer is “Not really” because...