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


In this chapter, we provided you with an overview of explainability and interpretability toolkits, which are important tools for understanding how AI models make decisions, as well as the role of PETs in ensuring data privacy and security. This chapter reviewed several toolkits, such as Google Vertex Explainable AI, Amazon SageMaker Clarify, model interpretability in Azure Machine Learning, and IBM’s AIF360. These toolkits enable developers to implement disciplined approaches and tools for the transparency and explainability of AI-enabled decision-making, while PETs, such as differential privacy, homomorphic encryption, and federated learning, help protect sensitive data.

This chapter also highlighted the importance of synthetically generated data in AI development to mitigate bias, improve fairness, and assure regulatory compliance within legal and ethical constraints. Synthetic data generation can be used to create datasets that are balanced and representative of...