Mixture Modeling of Individual Learning Curves
نویسنده
چکیده
We show that student learning can be accurately modeled using a mixture of learning curves, each of which specifies error probability as a function of time. This approach generalizes Knowledge Tracing [7], which can be viewed as a mixture model in which the learning curves are step functions. We show that this generality yields order-of-magnitude improvements in prediction accuracy on real data. Furthermore, examination of the learning curves provides actionable insights into how different segments of the student population are learning. To make our mixture model more expressive, we allow the learning curves to be defined by generalized linear models with arbitrary features. This approach generalizes Additive Factor Models [4] and Performance Factors Analysis [16], and outperforms them on a large, real world dataset.
منابع مشابه
Modeling the impact of learning environment and professor-student rapport on professional identification of medical students
Abstract: Introduction: Professional identification as a social process in order to define the individual and the professional community of the individual is affected by different environmental, individual and institutional factors. The aim of this study was to identify a model for examining the role of learning environment and professor-student rapport in predicting the professional iden...
متن کاملKinetics analysis of electrophoretic deposition using small signal and large signal modeling, Case study: Nano-Mullite suspension
Having sufficient and accurate understanding about kinetics of phenomena, could be an important reason for further technological progresses. Finding a white-box mathematical model for weight vs. time curves of Electrophoretic Deposition (EPD) using large and small signal analysis has been studied thoroughly in the present investigation. Weight-Time curves of nano-Mullite suspension have been tr...
متن کاملModeling Multimodal Continuous Heterogeneity in Conjoint Analysis - A Sparse Learning Approach
Consumers’ preferences can often be represented using a multimodal continuous heterogeneity distribution. One explanation for such a preference distribution is that consumers belong to a few distinct segments, with preferences of consumers in each segment being heterogeneous and unimodal. We propose an innovative approach for modeling such multimodal distributions that builds on recent advances...
متن کاملA Bayesian Hierarchical Mixture Approach to Individual Differences: Case Studies in Selective Attention and Representation in Category Learning
We demonstrate the potential of using a Bayesian hierarchical mixture approach to model individual differences in cognition. Mixture components can be used to identify latent groups of subjects who use different cognitive processes, while hierarchical distributions can be used to capture more minor variation within each group. We apply Bayesian hierarchical mixture methods in two illustrative a...
متن کاملHigh-order feature-based mixture models of classification learning predict individual learning curves and enable personalized teaching.
Pattern classification learning tasks are commonly used to explore learning strategies in human subjects. The universal and individual traits of learning such tasks reflect our cognitive abilities and have been of interest both psychophysically and clinically. From a computational perspective, these tasks are hard, because the number of patterns and rules one could consider even in simple cases...
متن کامل