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

References and further reading

  1. In this book, we use the terms interpretable and explainable AI interchangeably, but it is important to note that there are differences in opinion among the researchers about their definitions. Typically, explainable AI is focused on providing insights into how the AI system arrived at a particular decision, while interpretability is the discipline of making the AI system itself more understandable by making the individual components transparent. Transparency refers to systems where the inner workings are completely open and accessible, while explainable AI may only require that some level of understanding be possible. Generally speaking, explainable AI is more concerned with human-centered concerns such as usability and trustworthiness, while interpretable AI focuses more on providing information that can be used to improve the model or debug errors. However, both approaches are necessary for creating safe and effective AI systems.
  2. https://arxiv...