Kirjahaku

This book provides a full presentation of the current concepts and available techniques to make “machine learning” systems more explainable. The approaches presented can be applied to almost all the current “machine learning” models: linear and logistic regression, deep learning neural networks, natural language processing and image recognition, among the others.Progress in Machine Learning is increasing the use of artificial agents to perform critical tasks previously handled by humans (healthcare, legal and finance, among others). While the principles that guide the design of these agents are understood, most of the current deep-learning models are "opaque" to human understanding. Explainable AI with Python fills the current gap in literature on this emerging topic by taking both a theoretical and a practical perspective, making the reader quickly capable of working with tools and code for Explainable AI.Beginning with examples of what Explainable AI (XAI) is and why it is needed in the field, the book details different approaches to XAI depending on specific context and need. Hands-on work on interpretable models with specific examples leveraging Python are then presented, showing how intrinsic interpretable models can be interpreted and how to produce “human understandable” explanations. Model-agnostic methods for XAI are shown to produce explanations without relying on ML models internals that are “opaque.” Using examples from Computer Vision, the authors then look at explainable models for Deep Learning and prospective methods for the future. Taking a practical perspective, the authors demonstrate how to effectively use ML and XAI in science. The final chapter explains Adversarial Machine Learning and how to do XAI with adversarial examples.

This comprehensive book on Explainable Artificial Intelligence has been updated and expanded to reflect the latest advancements in the field of XAI, enriching the existing literature with new research, case studies, and practical techniques. The Second Edition expands on its predecessor by addressing advancements in AI, including large language models and multimodal systems that integrate text, visual, auditory, and sensor data. It emphasizes making complex systems interpretable without sacrificing performance and provides an enhanced focus on additive models for improved interpretability. Balancing technical rigor with accessibility, the book combines theory and practical application to equip readers with the skills needed to apply explainable AI (XAI) methods effectively in real-world contexts. Features: Expansion of the "Intrinsic Explainable Models" chapter to delve deeper into generalized additive models and other intrinsic techniques, enriching the chapter with new examples and use cases for a better understanding of intrinsic XAI models. Further details in "Model-Agnostic Methods for XAI" focused on how explanations differ between the training set and the test set, including a new model to illustrate these differences more clearly and effectively. New section in "Making Science with Machine Learning and XAI" presenting a visual approach to learning the basic functions in XAI, making the concept more accessible to readers through an interactive and engaging interface. Revision in "Adversarial Machine Learning and Explainability" that includes a code review to enhance understanding and effectiveness of the concepts discussed, ensuring that code examples are up-to-date and optimized for current best practices. New chapter on "Generative Models and Large Language Models (LLM)" chapter dedicated to generative models and large language models, exploring their role in XAI and how they can be used to create richer, more interactive explanations. This chapter also covers the explainability of transformer models and privacy through generative models. New "Artificial General Intelligence and XAI" mini-chapter dedicated to exploring the implications of Artificial General Intelligence (AGI) for XAI, discussing how advancements towards AGI systems influence strategies and methodologies for XAI. Enhancements in "Explaining Deep Learning Models" features new methodologies in explaining deep learning models, further enriching the chapter with cutting-edge techniques and insights for deeper understanding.