دانلود کتاب یادگیری ماشینی از کلاسیک تا شبکه های عمیق، ترانسفورماتورها و مدل های انتشار

Machine learning (ML) is a subtopic of artificial intelligence (AI) that acts as an umbrella and has resulted as an evolution of methods that have been studied and developed for many decades in different scientific communities and under different names, such as statistical learning, statistical signal processing, pattern recognition, adaptive signal processing, image processing and analysis, speech recognition, system identification and control, data mining and information retrieval, computer vision, and computational learning. The essence of what these disciplines have in common is that they all learn from data, and then make predictions. What one tries to learn from data is their underlying structure and regularities, via the development of a model, which can then be used to provide predictions. To this end, a number of different models have been developed, ranging from linear to various nonlinear ones. Also, a number of diverse approaches have been proposed. On the one side lie techniques that are based on optimizing, with respect to the adopted model, different cost functions, whose goal is to quantify the deviation between what one observes from data and what the estimated model predicts. On the other side lie probabilistic methods that attempt to explicitly model the statistical properties of the observed data. The goal of this book is to approach the machine learning discipline in a unifying framework, by presenting major paths and approaches that have been followed over the years, starting from the classics and moving to the most recent techniques. It is the author’s belief that all of them are valuable to the newcomer who wants to learn the secrets of this topic, from the applications as well as from the pedagogic points of view. The emphasis lies on the study and analysis of machine learning algorithms and methods and not on topics concerning the theory of learning itself and related performance bounds. In other words, the focus is on methods and algorithms closer to the applications level. The book is the outgrowth of more than four decades of the author’s experience in research and teaching various related courses. The book is written in such a way that individual (or pairs of) chapters are as self-contained as possible. So, one can select and combine chapters according to the focus he/she wants to give to the course he/she teaches, or to the topics he/she wants to grasp in a first reading. Some guidelines on how one can use the book for different courses are provided in the introductory chapter. Each chapter grows by starting from the basics and evolving to embrace more recent advances. Some of the topics had to be split into two chapters, such as sparsity-aware learning, Bayesian learning, probabilistic graphical models, Monte Carlo methods, and deep networks. The book addresses the needs of advanced graduate, postgraduate, and research students as well as of practicing scientists and engineers whose interests lie beyond black-box approaches. Also, the book can serve the needs of short courses on specific topics, e.g., sparse modeling, Bayesian learning, probabilistic graphical models, neural networks, and deep learning.