Artificial Intelligence can seem like magic when it accomplishes something impressive without being fully understood. In this short article, I make the case that adaptive learning in the classroom will actually work better when users understand what the algorithms are doing. There are many different models for adaptive learning, which I describe at the end of the article. An adaptive learning system is composed of several important elements: first, the content, like assessment questions and inst
Adaptive learning in the classroom will work better when users understand what the algorithms are doing. This article describes curriculum-based adaptive learning algorithms specifically designed to be easy to understand by teachers and students. Adaptive learning algorithms are designed to improve student outcomes. But, the algorithms aren't necessarily designed to measure whether the actions it takes are effective.
The quality of assessments, interventions, and overall product model can be much more influential on student outcomes than the algorithm itself. After each teaching cycle, the Mastery Learning Algorithm assesses whether a student learned. This algorithm supports embedded A/B tests (controlled experiments) that can reveal those learning resources that work best for each student. The core design of the algorithm isn't a machine learning model but a pedagogical model. Adaptive learning isn't a magic show, but understanding how it works can help you make it better.
When a student begins using the adaptive system, the algorithm gives them a short assessment of the topic assigned by the teacher. The algorithm evaluates precursor skills, which are easier skills that may support understanding in the current lesson.
