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 Fairlearn

Microsoft’s approach to fairness falls under the broader context of responsible AI where the fairness tenet accompanies characteristic features such as reliability and safety, privacy and security, inclusiveness, and transparency and accountability aspects. Fairlearn recognizes fairness as a sociotechnical problem and provides tools for evaluating fairness issues and mitigating them. It mainly comprises two key components, as follows:

  • Metrics that measure how the model negatively impacts different groups and can be used to perform a comparative analysis in terms of various aspects of fairness and accuracy
  • Algorithms for mitigating unfairness in various AI tasks and based on different definitions of fairness

The Fairlearn library consists of multiple packages—essentially, the modules for mitigating fairness-related harms in AI systems, including datasets, metrics, postprocessing, preprocessing, reductions, and experimental...