Structure Discovery: Tracing Student Knowledge

This lecture covers the assumptions behind Bayesian Knowledge Tracing (BKT) and introduces the Additive Factors Model (AFM) and Performance Factors Analysis (PFA) for tracing student knowledge. It also delves into Generalized Linear Mixed Effects Models, Item Response Theory, and the evaluation of student models using RMSE and AUC. The lecture further explores clustering algorithms such as K-Means, Spectral Clustering, and Hierarchical Agglomerative Clustering, discussing their assumptions, initialization, and selection of the optimal number of clusters.