Machine learning exercises using automated programming assessment tools
Beyond Simple Input-Output Assessment Tasks: Leveraging Automated Programming Assessment for Non-Trivial Courses
Artificial Intelligence
Summary
Teaching AI and machine learning requires mixing theory with practice, but grading practical exercises can be tricky. The authors suggest designing machine learning problems so that they have one clear correct answer, making it easier for automated tools to grade them accurately. This approach uses existing programming assessment platforms to help students learn AI more interactively. The authors do not introduce new grading technology but provide a fresh way to improve AI education.
What this means in practice
- •For online course designers: Create AI and machine learning exercises that integrate with automated programming assessment tools to provide scalable grading.
- •For programming contest platforms: Offer machine learning problems with unique correct solutions to improve automated assessment reliability and user experience.
A position paper. It proposes an approach and reports no results.
Authors
Artur Jordao
Abstract
The public visibility of Artificial Intelligence (AI) is growing rapidly, driven by the positive impact of its applications across diverse fields of knowledge. In this new chapter, courses that cover the foundations of AI and machine learning become essential for understanding their role and potential in contemporary society. Therefore, understanding fundamental concepts and elementary algorithms through the close integration of theory with practice is essential in AI courses. In this essay, we report our experience designing machine learning exercises for automated assessment tools in programming. It is worth mentioning that we are not developing a novel form of automated grading system. Instead, we propose a perspective that frames machine learning problems as input-output assessment tasks. From this perspective, each exercise admits a unique and deterministic answer and enables automated programming assessment tools (e.g., VPL for Moodle, Codeforces, and MOJ) to effectively support AI education. We believe this essay can encourage instructors to foster educational innovation by adopting more dynamic and interactive approaches to AI courses that integrate theory and practice. Importantly, this essay does not introduce an innovation in the use of AI for education; rather, it introduces an innovative approach to improving the learning of AI, particularly, machine learning.