MATLAB源码用于机器学习2017。

简介：
Machine learning is rapidly gaining prominence across a diverse spectrum of fields. It’s increasingly employed in engineering, notably for the development of autonomous vehicles. Furthermore, it’s utilized within the financial sector to forecast market trends. Medical professionals are also leveraging machine learning techniques for more accurate diagnoses. Despite the availability of numerous sophisticated packages from both commercial vendors and open-source repositories, it remains crucial to grasp the fundamental principles underlying these algorithms. Developing your own algorithms offers significant advantages, providing valuable insight into the functionality of existing commercial and open-source packages, as well as furnishing a strong foundation for creating bespoke Machine Learning software tailored specifically to your unique application requirements. MATLAB® was initially conceived with this very purpose in mind. Previously, scientists undertaking matrix operations relied on numerical software written in FORTRAN; however, at that time, utilizing computer languages necessitated a cumbersome process involving writing, compiling, linking, and executing code – a procedure that was both time-consuming and prone to errors. MATLAB introduced a scripting language that enabled users to address numerous challenges with concise scripts executed instantaneously. Complementing this were built-in visualization tools designed to enhance user comprehension of the results. The experience of writing MATLAB proved considerably more productive and enjoyable compared to working with FORTRAN. The central objective of MATLAB Machine Learning is to empower all users to effectively utilize MATLAB’s capabilities for tackling a broad array of learning problems. This book is structured around two distinct sections. The initial part—Chapters 1 through 3—provides essential background information on machine learning, including concepts like learning control which are not always directly associated with traditional machine intelligence; we introduce the term “autonomous learning” to encompass these varied disciplines. The subsequent portion of the book—Chapters 4 through 12—demonstrates complete MATLAB machine learning applications. Chapters 4 through 6 introduce the specific MATLAB features that streamline the implementation of machine learning techniques. The concluding chapters present illustrative examples demonstrating how these algorithms can be applied practically. Each chapter furnishes comprehensive technical background alongside practical suggestions regarding implementation strategies for each learning algorithm. Each example is meticulously implemented within a MATLAB script supported by a selection of relevant MATLAB functions. This book offers something valuable for anyone interested in machine learning and provides material that will enable individuals with an interest in other technological domains to explore how machine learning and MATLAB can assist them in addressing challenges within their respective areas of expertise.