Machine learning and deep learning have become necessary technologies for practitioners in the era of artificial intelligence. They are widely used in image recognition, natural language understanding, recommendation systems, speech recognition and other fields, and have achieved fruitful results. At present, many colleges and universities have offered machine learning and deep learning courses in artificial intelligence, software engineering, computer application and other majors. In addition, in order to allow students to master some big data analysis and visualization technologies, some non-computer majors also offer courses. courses related to machine learning. At the same time, some software developers in enterprises also want to learn real cases of machine learning and deep learning technology applications in related industries, without paying too much attention to some mathematical knowledge in machine learning and deep learning. However, there are not many reference books on the market that can meet the above requirements at the same time, and "Machine Learning and Deep Learning: Principles, Algorithms, and Practice (Using Python and TensorFlow)" happens to be a book that can meet the needs of college students and related practitioners A reference book on machine learning and deep learning.
The authors of this book are two senior industry experts with many years of corporate training experience. They explain machine learning and deep learning technology from simple to deep in a case-based way, so that readers can quickly master the principles of machine learning and deep learning. Principles and related applications. During the translation process of this book, we have read a lot of materials, and strive to provide readers with an easy-to-understand reference book on machine learning and deep learning that is close to practical applications.
At present, books on machine learning on the market mainly include two categories, namely books introducing machine learning theory for academic research and books on code manuals. Books on machine learning theory for academic research present the mathematical derivations and formulations involved in machine learning algorithms, but do little about practical applications to data. It is difficult for readers without a good theoretical background in statistics or mathematics to understand the content of this type of book. These books that deal with the principles of machine learning introduce the real-world challenges faced by data science practitioners, but rarely talk about the practice of machine learning. Code manual books mainly contain code and related documentation, the reasons for the lack of coding and the logical aspects of performing specific tasks. There is a distance between the academic study of machine learning and how it is used in industry. Therefore, we need a book that is based on the theory of machine learning and contains its related practice in the industry, and has a logical explanation in these practical cases. The purpose of this book is to fill the gap between the above two types of books (the gap between academic research and industrial application).
Excerpt from the preface of "Machine Learning and Deep Learning: Principles, Algorithms, Practice (Using Python and TensorFlow)"
