"Machine Learning for Engineers" Online Course Introduces Essential Skills to Engineering Students

Machine Learning for Engineers is a BYU PRISM online course that introduces engineering students to supervised and unsupervised learning methods, including regression, classification, clustering, and neural networks. The course has been widely used for self-study and in classrooms, with supporting videos, exercises, and open-source software.

Machine learning is an essential skill for engineers, offering powerful tools to analyze data, make predictions, and automate decisions. The Machine Learning for Engineers course developed by the BYU PRISM group provides undergraduate engineering students with theory and practice needed to apply ML methods to engineering problems.

Machine Learning for Engineers: https://apmonitor.com/pds/

At its core, machine learning combines linear algebra, probability, optimization, and computer science to enable systems to learn patterns from data. This course introduces the fundamentals of supervised and unsupervised learning (including regression, classification, clustering, and neural networks) and applies them to engineering applications such as energy, manufacturing, and chemical processes. The course follows an emphasis on theory and application. Each topic is introduced with the mathematical foundation needed to understand how algorithms work and why they succeed. This is followed by an applied case study or engineering example, allowing students to see how methods such as logistic regression or principal component analysis can be used in real design and decision-making contexts.

A distinguishing feature of the course is its hands-on approach. Students complete a series of programming exercises in either MATLAB or Python, where they build models, evaluate performance, and deploy solutions to engineering datasets. Each exercise is paired with a step-by-step solution video to follow along. This support helps students not only complete assignments but also gain deeper intuition about how machine learning can be applied in practice.

The second half of the course is a group project where teams select an engineering problem and apply machine learning techniques to solve it. Past projects have ranged from predicting material properties and optimizing reactor conditions to forecasting energy demand. These projects encourage students to bridge classroom concepts with open-ended engineering challenges, reinforcing both technical skill and creativity.

The reach of the course has extended well beyond the BYU classroom. All lecture and solution videos are made freely available on YouTube, as part of the broader PRISM Data-Driven Engineering initiative. The YouTube channel has now surpassed 10 million views, with the majority of learners joining from the United States and India, and significant participation from Europe, Latin America, and Africa. This global reach reflects the growing demand for accessible, engineering-focused content and highlights the role of open educational resources in broadening access to advanced training.