Undergraduate research experiences have been shown to increase student retention rates in STEM pathways, with a notable impact on students from Historically Underrepresented Groups (HUGs). However, undergraduate research experiences are often inaccessible to students, particularly in high-demand research areas and at large institutions with low faculty-to-student ratios.

We present an approach to broadening participation in computer science (CS) research by integrating a research project into a standard, upper-division optimization for machine learning (ML) course. We developed mini research projects which provided students with structured guidance to a new research area. In the projects, students were introduced to a recent publication in the area through a series of guided questions and then completed one of several recommended open-ended extensions for which they submitted a final report. In contrast to many hands-on undergraduate courses or programs that are focused on research, this approach introduces research in a large course in a scalable manner, lowering the barrier to entry for students and the implementation burden for instructors.

The results of our intervention revealed a positive impact on students’ academic and personal development. The majority of participants reported a moderate to large gain in readiness for further research, understanding of the engineering-mathematics research process, ability to read and comprehend scientific literature, and self- confidence. Specifically, these gains were present for two groups of students we were particularly interested in: students from HUGs and students with no prior research experience.