2026 ASEE Annual Conference & Exposition

As machine learning (ML) continues to reshape modern engineering practice, it is increasingly important for Mechanical Engineering Technology (MET) students to develop the skills needed to apply ML methods to practical engineering problems. However, many MET students lack strong backgrounds in mathematics and programming, which creates significant challenges in learning ML through conventional approaches. To respond to both student needs and workforce expectations, a new course titled Machine Learning for Applied Engineering has been developed and implemented in our MET program.

Due to capacity limitations in the existing MET curriculum, the course is structured as a single, all-in-one ML learning experience. Unlike traditional ML instruction in computer science, which typically spans multiple courses and emphasizes theoretical foundations and complex model development, this course is designed specifically for MET students with limited technical backgrounds. It focuses on teaching fundamental ML concepts and a small number of simple yet effective models that are sufficient to address many real-world engineering problems. The course combines lecture sessions that introduce core ML principles with hands-on labs where students apply ML tools to simplified engineering tasks. To lower the entry barrier, the course minimizes the use of advanced mathematics and coding in the early stages and gradually introduces more technical depth as students build confidence. This applied, accessible approach allows students to develop practical skills in ML without requiring prior expertise in computer science.

The paper will describe the overall design and implementation of the course, including the weekly structure, instructional strategies, and example lab activities. It will also present an evaluation of student learning outcomes based on project performance, quizzes, self-assessments, and feedback. Challenges encountered during the first offering of the course and lessons learned will be discussed to support future improvement. Course outlines and instructional strategies will be shared to support other institutions interested in developing similar application-focused ML courses for engineering technology or non-computer science programs.