Build and deploy your AI models successfully by exploring model governance, fairness, bias, and potential pitfalls
Purchase of the print or Kindle book includes a free PDF eBook
Key Features
- Learn ethical AI principles, frameworks, and governance
- Understand the concepts of fairness assessment and bias mitigation
- Introduce explainable AI and transparency in your machine learning models
Book Description
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.
What you will learn
- Understand explainable AI fundamentals, underlying methods, and techniques
- Explore model governance, including building explainable, auditable, and interpretable machine learning models
- Use partial dependence plot, global feature summary, individual condition expectation, and feature interaction
- Build explainable models with global and local feature summary, and influence functions in practice
- Design and build explainable machine learning pipelines with transparency
- Discover Microsoft FairLearn and marketplace for different open-source explainable AI tools and cloud platforms
Who this book is for
This book is for data scientists, machine learning engineers, AI practitioners, IT professionals, business stakeholders, and AI ethicists who are responsible for implementing AI models in their organizations.
Table of Contents
- A Primer on Explainable and Ethical AI
- Algorithms Gone Wild - Bias's Greatest Hits
- Opening the Algorithmic Blackbox
- Operationalizing Model Monitoring
- Model Governance - Audit, and Compliance Standards & Recommendations
- Enterprise Starter Kit for Fairness, Accountability and Transparency
- Interpretability Toolkits and Fairness Measures
- Fairness in AI System with Microsoft FairLearn
- Fairness Assessment and Bias Mitigation with FairLearn and Responsible AI Toolbox
- Foundational Models and Azure OpenAI
Dawe, Heather: - Heather Dawe, MSc. is a renowned data and AI thought leader with over 25 years of experience in the field. Heather has innovated with data and AI throughout her career, highlights include developing the first data science team in the UK public sector and leading on the development of early machine learning and AI assurance processes for the National Health Service (NHS) in England. Heather currently works with large UK Enterprises, innovating with data and technology to improve services in the health, local government, retail, manufacturing, and finance sectors. A STEM Ambassador and multidisciplinary data science pioneer, Heather also enjoys mountain running, rock climbing, painting, and writing. She served as a jury member for the 2021 Banff Mountain Book Competition and guest edited the 2022 edition of The Himalayan Journal. Heather is the author of several books inspired by mountains and has written for national and international print publications including The Guardian and Alpinist.
Masood, Adnan: - Adnan Masood, PhD is a visionary leader practitioner in the field of artificial intelligence, with over 20 years of experience in financial technology and large-scale systems development. He drives the firm's digital transformation, machine learning, and AI strategy. Dr. Masood collaborates with renowned institutions like Stanford AI Lab and MIT CSAIL, holds several patents in AI and machine learning, and is recognized by Microsoft as an AI MVP and Regional Director. In addition to his work in the technology industry, Dr. Masood is a published author, international speaker, STEM robotics coach, and diversity advocate.
