Understanding Machine Learning: From Theory to Algorithms Shai Shalev-Shwartz and Shai Ben-David is an English-language textbook that focuses on the theoretical and practical aspects of machine learning. This work covers the foundations and algorithmic paradigms behind automated learning and is intended for students in higher education.
The book offers an in-depth and structured introduction to machine learning, with attention to both the basic principles and complex topics such as the computational complexity of learning, convexity, and stability. In addition, it introduces important algorithmic paradigms such as stochastic gradient descent, neural networks, and structured output learning.
Furthermore, the textbook discusses cutting-edge theoretical concepts, including the PAC-Bayes approach and compression-based bounds. This makes it suitable for students and professionals from various fields such as computer science, mathematics, and engineering who want to gain insight into both the theory and the algorithmic approaches to machine learning.
Topics such as Machine learning, COMPUTERS / Data Science / Machine Learning and Computing: Textbooks & Study Guides form the content context of this book.