Mehr lesen
The book begins by presenting the necessary mathematical foundations in an accessible, engineering-centered way and then builds up machine learning (ML) concepts step by step, always linking them to engineering scenarios and real-world datasets. Engineering is being transformed by the data revolution: from smart manufacturing and sensor-rich infrastructure to predictive maintenance, autonomous systems, and intelligent product design. However, despite the explosion of ML in industry, there is a shortage of resources that systematically teach ML methods to engineers from a perspective of engineering applications and in a language and examples they understand. This book addresses this gap, helping engineers acquire both the mathematical confidence and ML know-how to lead and innovate in a rapidly evolving field.
The book demonstrates methods through both theoretical derivation and hands-on Python code, empowering readers to move from understanding to practical implementation. (An online Python code portal will be set up for the book.) Finally, the book covers emerging and specialized topics, such as physics-informed neural networks and agentic architectures, showing how ML can be tailored to leverage engineering knowledge and domain constraints for complex engineering applications.
Über den Autor / die Autorin
Dr. Yan Jin is a professor of the Department of Aerospace and Mechanical Engineering at the University of Southern California and Director of USC IMPACT Laboratory. He received his Ph.D. from the University of Tokyo and conducted postdoctoral research at Stanford University. His current research interests include design theory and methods, machine learning and its applications in engineering design, manufacturing, knowledge capturing, complex and self-organizing adaptive systems. Dr. Jin was a UPS Foundation visiting professor at Stanford University (2004–2006), a guest professor at Shanghai Jiao Tong University (2011–2014), and a senior engineer (adjunct) at RAND Corporation (2009–2013). Dr. Jin is a fellow of American Society of Mechanical Engineers, 2010 (ASME).
Zusammenfassung
The book begins by presenting the necessary mathematical foundations in an accessible, engineering-centered way and then builds up machine learning (ML) concepts step by step, always linking them to engineering scenarios and real-world datasets. Engineering is being transformed by the data revolution: from smart manufacturing and sensor-rich infrastructure to predictive maintenance, autonomous systems, and intelligent product design. However, despite the explosion of ML in industry, there is a shortage of resources that systematically teach ML methods to engineers from a perspective of engineering applications and in a language and examples they understand. This book addresses this gap, helping engineers acquire both the mathematical confidence and ML know-how to lead and innovate in a rapidly evolving field.
The book demonstrates methods through both theoretical derivation and hands-on Python code, empowering readers to move from understanding to practical implementation. (An online Python code portal will be set up for the book.) Finally, the book covers emerging and specialized topics, such as physics-informed neural networks and agentic architectures, showing how ML can be tailored to leverage engineering knowledge and domain constraints for complex engineering applications.
