Wow! eBook
Applied Machine Learning Explainability Techniques: Make ML models explainable and trustworthy for practical applications using LIME, SHAP, and more
Author(s): Aditya Bhattacharya (Author)
- Publisher: Packt Publishing
- Publication Date: 29 July 2022
- Language: English
- Print length: 306 pages
- ISBN-10: 1803246154
- ISBN-13: 9781803246154
Book Description
Leverage top XAI frameworks to explain your machine learning models with ease and discover best practices and guidelines to build scalable explainable ML systems
Key Features
- Explore various explainability methods for designing robust and scalable explainable ML systems
- Use XAI frameworks such as LIME and SHAP to make ML models explainable to solve practical problems
- Design user-centric explainable ML systems using guidelines provided for industrial applications
Book Description
Explainable AI (XAI) is an emerging field that brings artificial intelligence (AI) closer to non-technical end users. XAI makes machine learning (ML) models transparent and trustworthy along with promoting AI adoption for industrial and research use cases.
Applied Machine Learning Explainability Techniques comes with a unique blend of industrial and academic research perspectives to help you acquire practical XAI skills. You’ll begin by gaining a conceptual understanding of XAI and why it’s so important in AI. Next, you’ll get the practical experience needed to utilize XAI in AI/ML problem-solving processes using state-of-the-art methods and frameworks. Finally, you’ll get the essential guidelines needed to take your XAI journey to the next level and bridge the existing gaps between AI and end users.
By the end of this ML book, you’ll be equipped with best practices in the AI/ML life cycle and will be able to implement XAI methods and approaches using Python to solve industrial problems, successfully addressing key pain points encountered.
What you will learn
- Explore various explanation methods and their evaluation criteria
- Learn model explanation methods for structured and unstructured data
- Apply data-centric XAI for practical problem-solving
- Hands-on exposure to LIME, SHAP, TCAV, DALEX, ALIBI, DiCE, and others
- Discover industrial best practices for explainable ML systems
- Use user-centric XAI to bring AI closer to non-technical end users
- Address open challenges in XAI using the recommended guidelines
Who this book is for
This book is for scientists, researchers, engineers, architects, and managers who are actively engaged in machine learning and related fields. Anyone who is interested in problem-solving using AI will benefit from this book. Foundational knowledge of Python, ML, DL, and data science is recommended. AI/ML experts working with data science, ML, DL, and AI will be able to put their knowledge to work with this practical guide. This book is ideal for you if you’re a data and AI scientist, AI/ML engineer, AI/ML product manager, AI product owner, AI/ML researcher, and UX and HCI researcher.
Table of Contents
- Foundational Concepts of Explainability Techniques
- Model Explainability Methods
- Data-Centric Approaches
- LIME for Model Interpretability
- Practical Exposure to Using LIME in ML
- Model Interpretability Using SHAP
- Practical Exposure to Using SHAP in ML
- Human-Friendly Explanations with TCAV
- Other Popular XAI Frameworks
- XAI Industry Best Practices
- End User-Centered Artificial Intelligence
Editorial Reviews
Review
“Most machine learning approaches are black boxes. The days of learning how they work out of curiosity are over; explaining how ML predictions are made is now becoming legally mandatory. This book details effective ways to achieve explainability. A must-have resource for all ML practitioners, from beginners to experts.”
Dr. Yogesh Kulkarni, Principal Architect, CTO office, Icertis
“Explainability is going to play a big role in the usability of models in a range of important applications. The author takes the very organized approach of starting with the basics, discussing common libraries such as SHAP and LIME, and then expanding to a broader horizon with other XAI frameworks. The concepts have been presented clearly and are accompanied by real-world examples and intuitive diagrams, making it a great read. The code excerpts are succinct and adequate. This will be really helpful for readers who are getting started in XAI.”
Saptarshi Goswami, Digital Transformation Lead, IT & Innovation Cell, at Department of Higher Education, Govt. of WB
“This book lucidly demonstrates the concepts and algorithms related to image generation, along with providing executable code. This is the perfect book for machine learning researchers and engineers to build a strong foundation in this domain.”
Sabyasachi Mukhopadhyay, Research Scholar, Center for Computational Data Science, IIT Kharagpur, Google Developer Expert in Machine Learning
“Explainable AI is a multi-disciplinary perspective that combines learnings from the fields of science, technology, and research with the mental model of users. The author of this book has done a fantastic job in portraying this multi-disciplinary perspective through detailed explanations of the concepts, interesting examples, graphical representations, and step- by- step code examples that anyone with foundational knowledge of Python can follow. The book provides knowledge about XAI with a unique blend of recommendations from industrial and academic research practices. I highly appreciate the efforts taken by the author to explain every topic with sufficient details that can be followed by beginners to experts of machine learning. This is highly recommended for all ML practitioners!”
Shreya Bhattacharya –– solar physics researcher at Royal Observatory of Belgium
About the Author
Aditya Bhattacharya is an Explainable AI Researcher at KU Leuven with the mission to bring AI closer to end-users.
Previously, I had worked as the AI Lead and a data scientist at West Pharmaceuticals. I have an overall exposure of 6 years in Data Science, Machine Learning, IoT, and Software Development. I have led more than 20 AI projects and programs democratizing AI practice for West and Microsoft. In West, I have contributed to forming the AI team and developed end-to-end solutions from scratch. I also have people management experience of about 2 years at West and have led and managed a global team of 10+ members.
