New Textbook Teaches Students How to Apply Machine Learning To Real World Problems

Two faculty members in the UC Davis College of Engineering, Setareh Rafatirad and Houman Homayoun, recently published a new textbook on applied machine learning that not only explains key concepts of machine learning, but also provides hands-on examples to empower readers to be successful in problem solving.

Machine Learning for Computer Scientists and Data Analysts, From An Applied Perspective is designed to teach undergraduate and graduate students what machine learning algorithm best suits their problem and how to optimize the algorithm. It is currently available for free to all UC Davis students, faculty and staff through Springer Publishing Company.

Rafatirad is an assistant professor of teaching in the Department of Computer Science and Homayoun is an associate professor in the Department of Electrical and Computer Engineering at UC Davis. Other co-authors of the book are colleagues from George Mason University and Mississippi State University.

“We are planning to use the materials in various courses at UC Davis,” Homayoun said. “In fact, Dr. Rafatirad has already been using the material for her highly enrolled undergrad machine learning course.”

Deep understanding of concepts

The textbook introduces readers to the theoretical and applied aspects of machine learning algorithms, starting from simple neuron basics and carrying through complex neural networks. It also includes lessons on generative adversarial neural networks and graph convolution networks.

Most importantly, according to Homayoun, the book helps readers to understand the concepts of machine learning and enables them to develop the skills necessary to choose an appropriate machine learning algorithm for a domain problem they wish to solve.

The textbook includes numerous case studies ranging from simple time-series forecasting to object recognition and recommender systems using massive databases. It also provides practical implementation examples and assignments for the readers to practice and improve their programming capabilities for the machine learning applications. It starts with basic math required for learning machine learning. The lessons then progress from simple neuron basics, to complex neural networks, generative AI, online learning and graph convolutional networks. There are also a plethora of case studies on smart health, cybersecurity, data center resource management and more.

“In my opinion, this book is unique in the sense that in addition to delivering an applied perspective. It also caters a solid background of basics and mathematics related to machine learning techniques," Rafatirad said. “Anyone—whether being a data analyst, student or engineer—can benefit from this book if they are interested in learning the concepts of machine learning or obtaining hands-on experience with various machine learning techniques.”