A Guidline for Creating Assessments in Machine Learning Education

A Guidline for Creating Assessments in Machine Learning Education

Çakıcı, Kerem (TU Delft Electrical Engineering, Mathematics and Computer Science)

Migut, M.A. (mentor)
Specht, M.M. (mentor)
Özkan, B. (graduation committee)

Delft University of Technology

Computer Science and Engineering

CSE3000 Research Project

2022-06-22

Even though machine learning field is growing rapidly, research on education of machine learning is scarce. In this paper a research about creating assessments in the machine learning’s context is presented. The aim of the research is to answer how to design assessments that reliably show progress on a module in machine learning. Learning outcomes and Bloom’s taxonomy are used to make the research reproducible, and draw conclusions. One of the main conclusions drawn in this paper is that verbs that are used in learning outcomes can also be used to find the appropriate question type (e.g. open ended, multiple-choice) to assess that learning outcome. Additionally, this paper concludes there is no strict procedure of creating assessment questions. Therefore, a guideline is created by the researcher and presented in the paper. Lastly, four questions are created using this guideline and evaluated with interviews with three machine learning professors.

Machine Learning
Assessment
Learning outcomes
Bloom's taxonomy
Education

http://resolver.tudelft.nl/uuid:26e3f1df-fb9d-4f68-a563-51e9a653c8b5

Student theses

bachelor thesis

© 2022 Kerem Çakıcı