Understanding Explainable AI
Description
Understanding Explainable AI is a clear and practical guide to making sense of how modern AI systems think, decide, and justify their predictions. This book introduces the foundations of Explainable Artificial Intelligence (XAI), explaining why interpretability matters, what types of explanations exist, and how ethical, fair, and responsible AI can be achieved.
Beginning with core concepts such as black-box versus white-box models and interpretable data representations, the book builds a strong conceptual and mathematical base, supported by intuitive Python examples that make complex ideas accessible to students, practitioners, and early-career researchers. Guiding you from simple linear models and decision trees to advanced local and global explanation techniques, the book explores widely used XAI methods such as LIME, SHAP, counterfactuals, partial dependence plots, and surrogate models. It then moves deeper into neural network interpretability, feature visualization, and concept detection, helping you understand what deep models actually learn. The final chapters demonstrate how XAI techniques are applied in real-world scenarios across industries, showing how interpretability improves confidence, accountability, and decision-making.
By the end of the book, you will be equipped to design, analyze, and deploy AI systems that are not only accurate, but also transparent and trustworthy.
What You Will Learn:
- Ethics, Fairness, and Responsible AI
- Understanding Models and Data with Black-Box vs White-Box Models
- Implementing models and principles with simple Python Examples
- Demonstrating Local Model-Agnostic XAI Methods
- Applications of XAI in Healthcare, Finance, Agriculture, and more
Who This Book Is For:
AI Engineers, Researchers, and Students
More details
Persons
Dr Ramchandra Sharad Mangrulkar is a Professor in the Department of Information Technology at Dwarkadas J Sanghvi College of Engineering in Mumbai, India. He holds various memberships in professional organizations such as IEEE, ISTE, ACM, and IACSIT. He completed his Doctor of Philosophy (Ph.D) in Computer Science and Engineering from S.G.B. Amravati University in Maharashtra, and Master of Technology (MTech) degree in Computer Science and Engineering from the National Institute of Technology, Rourkela. Dr Mangrulkar is proficient in several technologies and tools, including Microsoft's Power BI, Power Automate, Power Query, Power Virtual Agents, Google's Dialog Flow, and Overleaf.
Dr Nonita Sharma is an Associate Professor in the Department of Information Technology at the Indira Gandhi Delhi Technical University for Women, Delhi. Dr Sharma has an active research publication record in SCI/SCOPUS indexed journals such as Springer, Elsevier, Inderscience, and Bentham Science, with works addressing ensemble learning, disease forecasting, blockchain frameworks, and software fault prediction.
Dr Monika Mangla is working as an Associate Professor in the Department of Information Technology at Dwarkadas J Sanghvi College of Engineering, Mumbai. She has 24 years of teaching experience at undergraduate and postgraduate levels to her credit. Her interest areas include IoT, Cloud Computing, Algorithms and Optimization, Location Modelling and Machine Learning. She has authored a book on Algorithms published by Pearson. She has also edited scholarly volumes published by Pearson, Taylor & Francis, CRC Press, Wiley, and Apple Academic Press. Dr Monika has an active research publication record by publishing research articles in SCI and SCOPUS-indexed journals published by reputed publishers, namely Springer, Elsevier, and Bentham Science. She has actively worked in the domain of ensemble learning, disease forecasting, software fault prediction, and photovoltaic power forecasting.
Dr Nilesh Patil is working as an Associate Professor in the Department of Computer Engineering at Dwarkadas J Sanghvi College of Engineering, Mumbai. He has 20 years of teaching experience at undergraduate and postgraduate levels to his credit. His interest areas include Blockchain Technology, Machine Learning, and Cyber Security. He has guided several projects at the UG and PG level. He is also supervising PhD Research Scholars. Dr Nilesh has an active research publication record by publishing research articles in SCI and SCOPUS-indexed journals published by reputed publishers like Springer, Elsevier. He has been associated with several reputed conferences as a Reviewer and Session chair. He also has 3 patents and 1 copyright to his credit. He is a life member of ISTE and a senior member of IEEE.
Content
Chapter 1: Introduction to Explainable AI.- Chapter 2: Understanding Models and Data.- Chapter 3: Linear Models.- Chapter 4: Decision Trees and Rules.- Chapter 5: Local Explanation Techniques.- Chapter 6: SHAP and Shapley Values.- Chapter 7: Global Explanation Techniques.- Chapter 8: Understanding Deep Networks.- Chapter 9: Applications of XAI.