Bo Han - Böcker

The subject of this book centresaround trustworthy machine learning under imperfect data. It is primarily designed forscientists, researchers, practitioners, professionals, postgraduates andundergraduates in thefield of machine learning and artificial intelligence. The book focuseson trustworthy deep learning under various types of imperfect data, includingnoisy labels, adversarial examples, and out-of-distribution data. It coverstrustworthy machine learning algorithms, theories, and systems. The main goal of the book is to provide students and researchers in academia with anunbiased and comprehensive literature review. More importantly, it aims to stimulateinsightful discussions about the future of trustworthy machine learning. By engaging the audiencein more in-depth conversations, the book intends to spark ideas for addressing coreproblems in this topic. For example, it will explore how to build up benchmark datasets innoisy-supervised learning, how to tackle the emerging adversarial learning, andhow to tackle out-of-distribution detection. For practitioners in the industry,this book will present state-of-the-art trustworthy machine learning methods tohelp them solve real-world problems in different scenarios, such as onlinerecommendation and web search. While the book will introduce the basics ofknowledge required, readers will benefit from having some familiarity withlinear algebra, probability, machine learning, and artificial intelligence. Theemphasis will be on conveying the intuition behind all formal concepts,theories, and methodologies, ensuring the book remains self-contained at a highlevel.