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

Getting started with interpretable methods

In the world of AI and ML, black box models are those that cannot be easily interpreted or understood by humans. This contrasts with white-box ML models, which can be easily interpreted and understood. White-box models are models whose inner logic, functionality, and programming steps are transparent. As a result, the decisions made by them can be understood. The most common white-box models include decision trees, as well as linear regression models, and Bayesian networks. Such models, in particular, linear models and generalized linear models such as logistic regression, have been commonly used within enterprises for well over a decade. While advances in black-box models such as neural networks and XGBoost typically improve on the predictive power of their equivalent logistic regression counterparts, this is at the expense of transparency.

Black-box models are, by definition, hard to look into and interpret. When AI produces insights...