Statistical Foundations of Machine Learning, Second Edition

The book is dedicated to all students interested about machine learning which are not satisfied with running some lines of (deep-learning) code but are eager to know about assumptions, limitations, and perspectives of this discipline. When I was a student, my dream was to become an AI researcher and save humankind with intelligent robots. For several reasons, I quit such ambition (but you never know). In exchange, I discovered that machine learning is much more than a conventional research domain since it aims to make automatic the scientific process bringing from observations to knowledge.

The first version of this book was made publicly available in 2004 with two objectives and one ambition. The first objective was to provide a handbook to ULB students since I was (and still am) strongly convinced that a decent course should come with a decent handbook. The second objective was to group all the material that I consider fundamental (or at least essential) for a Ph.D. student to undertake a thesis in my lab. At that time there were already plenty of excellent machine learning reference books. However, most of the existing work concealed (or did not make explicit enough, notably because of incomplete or inconsistent notation) important statistical assumptions underlying the process of inferring models from data.