Learning Cognitive Models using Neural Networks

TL;DR

This paper introduces CogRL, a neural network-based framework that automatically learns cognitive models in complex domains without student data or extensive human input, improving adaptive tutoring.

Contribution

CogRL enables automatic cognitive model discovery and skill parameter estimation in ill-structured domains without student data or human knowledge engineering.

Findings

CogRL accurately discovers cognitive models in multiple domains.

Representations learned by CogRL correlate with student performance data.

The framework reduces the need for human-authored models and student data.

Abstract

A cognitive model of human learning provides information about skills a learner must acquire to perform accurately in a task domain. Cognitive models of learning are not only of scientific interest, but are also valuable in adaptive online tutoring systems. A more accurate model yields more effective tutoring through better instructional decisions. Prior methods of automated cognitive model discovery have typically focused on well-structured domains, relied on student performance data or involved substantial human knowledge engineering. In this paper, we propose Cognitive Representation Learner (CogRL), a novel framework to learn accurate cognitive models in ill-structured domains with no data and little to no human knowledge engineering. Our contribution is two-fold: firstly, we show that representations learnt using CogRL can be used for accurate automatic cognitive model discovery without using any student performance data in several ill-structured domains: Rumble Blocks, Chinese Character, and Article Selection. This is especially effective and useful in domains where an accurate human-authored cognitive model is unavailable or authoring a cognitive model is difficult. Secondly, for domains where a cognitive model is available, we show that representations learned through CogRL can be used to get accurate estimates of skill difficulty and learning rate parameters without using any student performance data. These estimates are shown to highly correlate with estimates using student performance data on an Article Selection dataset.