Machine learning, a branch of artificial intelligence (AI) research, is accelerating human-machine interactions in this developing world. MATLAB is a mathematical tool aiding in such interactions. This book presents MATLAB implementation in machine learning.

This book consists of 12 chapters grouped into two parts, “Introduction to Machine Learning” and “MATLAB Recipes for Machine Learning.” The twelve chapters include: “An Overview of Machine Learning,” “The History of Autonomous Learning,” “Software for Machine Learning,” “Representation of Data for Machine Learning in MATLAB,” “MATLAB Graphics,” “Machine Learning Examples in MATLAB,” “Face Recognition with Deep Learning,” “Data Classification,” “Classification of Numbers Using Neural Networks,” “Kalman Filters,” “Adaptive Control,” and “Autonomous Driving.” The authors provide short introductions to both machine learning and MATLAB and emphasize the usage of MATLAB.

The first part provides details about machine learning and its software and the history of autonomous learning. In chapter 1, the authors focus on the elements, learning machine, taxonomy, and learning methods of machine learning. They include data, models, and training such as supervised, unsupervised, semisupervised, and online learning in the elements of machine learning. Furthermore, the authors describe autonomous learning methods, including regression, neural networks (NN), support vector machines (SVMs), decision trees, and expert systems. Chapter 2 presents a brief history of autonomous learning, covering AI, learning control, machine learning, and insight into its future. In chapter 3, the authors introduce software for machine learning, that is, MATLAB and its toolboxes (statistics and machine learning, NN, computer vision system, and system identification) and Princeton Satellite Systems products (the core control toolbox and target tracking module). In addition, they also discuss products for machine learning and optimization, including R, scikit-learn, LIBSVM, LOQO, SNOPT, GLPK, CVX, SeDuMi, and YALMIP.

In the second part, the authors discuss data representation and classification, graphics, machine learning examples, face recognition, numbers classification, Kalman filters, adaptive control, and autonomous driving through MATLAB. Chapters 4 and 5 discuss the basics of MATLAB implementation, focusing on representation of data and graphics for machine learning. In chapter 6, the authors briefly describe machine learning examples such as NN, face recognition, data classification, Kalman filters, adaptive control, and autonomous driving. In addition, the authors further describe each of the machine learning examples separately in chapters 7 to 12.

Specifically, subsections found in most chapters--“Problem,” “Solution,” and “How It Works”--make this book an interesting read. Programming blocks in MATLAB are helpful to beginners and advanced learners, as well as graduate students and professionals working in various aspects of machine learning implementation. Most of the chapters conclude with a summary and references, and the book ends with an index.

More reviews about this item: Amazon