This introductory text builds a bridge between mathematical foundations and machine learning algorithms. Assuming only a basic background in mathematics, statistics, and scientific computing, it develops the key concepts underlying machine learning through three fundamental questions: Which samples are important? Which features are important? How can we generate new samples? Topics include support vector machines, sparse learning, optimization, information theory, and generative models.

Emphasizing mathematical understanding rather than black-box use of software, the book is suitable for advanced undergraduate students, beginning graduate students, and practitioners seeking a rigorous introduction to machine learning.

Stefan Janaqi earned his PhD in Graph Theory from ENSIMAG before joining ELF Antar France as a postdoctoral researcher in 1995, where he investigated the question of confidence in machine learning models. He has since worked as a lecturer, researcher, and consultant in data science, developing models for applications ranging from the petroleum industry and medicine to the analysis of movement and musical signatures. Decades of experience in research and industry inform his teaching approach, which bridges theoretical foundations and real-world applications for students and practitioners alike.