Machine Learning

This book is designed to provide a well-structured, comprehensive, and practical textbook on machine learning for undergraduate and graduate students in related fields. Through clear and accessible explanations, this book allows readers go master the concepts and techniques of machine learning, equipping them with the ability to solve real-world problems.

A distinctive feature of this book is its emphasis on interpretability. In the world of machine learning, models need not only to be accurate but also to be understandable and explainable. For students, understanding the underlying principles and logic of algorithms is more important than simply using them as black boxes. Therefore, each chapter in this textbook not only introduces the mathematical background and implementation principles of the algorithms but also demonstrates them through detailed Python code, helping readers understand how each algorithm works and providing valuable insights.

From the foundational concepts of linear regression and logistic regression to more complex techniques such as deep neural networks, convolutional neural networks, and recurrent neural networks, this book covers the full spectrum of classical algorithms and cutting-edge technologies in machine learning. We also provide in-depth discussions on ensemble learning, reinforcement learning, and Transformer models, addressing some of the most popular topics in the field. Through real-world case studies, we connect these algorithms with practical applications, helping readers better understand how they are used in various scenarios.

While focusing on theoretical learning, we also emphasize the development of practical skills. The case studies in each chapter are based on real-world data and cover a variety of domains, including classification, regression, image processing, and natural language processing. Through these case studies, readers will not only grasp the ideas behind the algorithms but also experience how to apply these theories to solve actual problems.

Finally, this book includes a special section on large language models, showcasing how machine learning has evolved into today's cutting-edge technology. It guides readers toward the frontier of artificial intelligence, highlighting breakthroughs in natural language understanding and generation. This marks not just an extension of machine learning techniques, but also their profound impact in the realm of language processing.

This book is suitable not only for academic teaching but also for scholars and practitioners who wish to deepen their understanding of machine learning. We hope that it helps readers strengthen their theoretical foundation, enhance their practical skills, and pave the way for engaging with frontier research and innovation in this field.

A comprehensive ML textbook for undergraduate and graduate students Emphasizes interpretability with mathematical foundations and Python code Features real-world case studies in reliability and engineering analytics Includes a special section on large language models (LLMs)

Autorentext

Xufeng Zhao is a Professor at the College of Economics and Management, Nanjing University of Aeronautics and Astronautics, China. He received his Ph.D. from Aichi Institute of Technology (Japan), where he also completed postdoctoral research, and subsequently worked as a postdoctoral researcher at Qatar University. His research interests include machine learning, reliability and maintenance modeling, and prognostics and health management (PHM). He has authored four books with Springer and over 100 peer-reviewed journal papers. His editorial roles include Associate Editor for IEEE Transactions on Reliability , the International Journal of Reliability, Quality and Safety Engineering , Stochastic Models , and Communications in Statistics Theory and Methods . He additionally chairs the Program Committee for the ISSAT International Conference on Reliability & Quality in Design.

Inhalt

1. Introduction to Machine Learning.- 2. Fundamentals of Machine Learning.- 3. Linear Regression.- 4. Logistic Regression.- 5. Deep Neural Network.- 6. Convolutional Neural Network.- 7. Recurrent Neural Networks.- 8. Ensemble Learning.- 9. Reinforcement Learning.- 10. Transformer.- Reference.