Machine Learning

Machine Learning: From the Classics to Deep Networks, Transformers, and Diffusion Models, 3rd Edition, by Sergios Theodoridis provides a comprehensive textbook for graduate engineering courses. The text establishes essential theoretical principles while introducing modern computational architectures. It guides students through canonical probability concepts and current learning methods to support advanced coursework and practical application.

Coverage spans classical foundational topics, including least squares regression, maximum likelihood methods, Bayesian decision theory, logistic regression, and decision trees. Building on these fundamentals, the volume explores advanced architectures such as perceptrons, multilayer perceptrons, convolutional neural networks, recurrent neural networks, capsule networks, deep belief networks, GANs, and VAEs. Extended coverage in this edition highlights attention transformers, large language models, self-supervised learning, and diffusion models.

To support practical exercise and model implementation, most chapters include computer exercises structured in MATLAB and Python, while dedicated deep learning chapters provide PyTorch exercises. This technical foundation prepares graduate students in electrical, computer, and mechanical engineering to analyze, select, and deploy machine learning algorithms across diverse engineering applications.