Date of Award

Summer 8-19-2023

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Engineering Education

First Advisor

David Hall

Abstract

Artificial intelligence and machine learning (ML) have exploded in use, accessibility, and awareness in the past few years, particularly with the release of ChatGPT in late 2022. Advances in end-user ML tools are accelerating the development of ML applications, lowering the technical barrier of entry for users outside of the computer science (CS) community. Access to ML education within STEM is mostly limited to upper-level computer science courses that have deep pre-requisite requirements or to introductory workshops that yield limited ML skills. Despite the critical need for ML education, there is a lack of guidance in instructional design for applied ML courses and no framework for incorporating end-user ML hardware and software tools into courses. Six applied ML courses were designed and developed for engineering and engineering technology students at Louisiana Tech University. The courses utilized several ML hardware and software platforms for computer vision, predictive maintenance, and reinforcement learning applications. A set of five course threads were defined to group related topics within the courses to develop student knowledge, skills, and attitudes for applied ML. These threads were used to categorize and assess learning and self-efficacy of the students enrolled in the courses. This work culminated in the development of the Impact Framework. This educational framework gauges the time and effort spent within a course by assigning course threads to buckets - broader categories of knowledge, skills, and attitudes. Impact is measured as the product of time spent within an activity and the level of complexity of that activity according to the Structure of Learning Outcomes (SOLO) taxonomy. The Impact Framework was demonstrated by applying it to the six courses designed and delivered as part of this work. The measurement of impact was used to assess the ability of an end-user ML tool to expand the scope of ML course content while reducing the skills necessary to accomplish meaningful ML projects. The Impact Framework may also be applied to other subjects and disciplines to assist course designers in organizing and balancing course content and activities.

Download

Share

COinS