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

Local Interpretable Model-Agnostic Explanations

Local Interpretable Model-Agnostic Explanations (LIME) is an ML explainability technique. It is a model-agnostic method, and it is local in that it only explains the prediction for a single instance. LIME works by perturbing the input data and observing how this affects the output of the model. For each perturbation, LIME calculates an importance score, which represents how important that feature was in determining the predicted outcome. The final explanation is generated by taking a weighted sum of all these importance scores.

LIME works by approximating the decision boundary around the instance to be explained (the so-called local model), and then computing how changes to input values would affect predictions made by this model (the so-called perturbation). This approach allows us to understand which input features are most important in determining the predicted output, without having to rely on global assumptions about feature importance...