Probabilistic student models: Bayesian Belief Networks and Knowledge Space Theory

Villano, Michael

doi:10.1007/3-540-55606-0_58

Cited by 58 publications

(46 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…LFA automatically discovers cognitive models, but is limited to the space of the human-provided factors. Other works such as Pavlik et al [2009], Villano [1992] are less dependent on human labeling, but the models generated may be hard to interpret. In contrast, the SimStudent approach has the benefit that the acquired production rules have a precise and usually straightforward interpretation.…”

Section: Discussionmentioning

confidence: 99%

“…There has been previous effort in this direction. Researchers have used machine learning [Cen et al, 2006, Pavlik et al, 2009, Villano, 1992, Tatsuoka, 1983, Barnes, 2005, Baffes and Mooney, 1996 and artificial intelligence [Langley and Ohlsson, 1984, Burton, 1982, Sleeman and Smith, 1981, VanLehn, 1990 techniques to automatically construct cognitive models. Our work also applies machine learning and artificial intelligence tools to create intelligent learning agents, and takes one more step in this direction by comparing the system with human learning curve data.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Integrating representation learning and skill learning in a human-like intelligent agent

Matsuda

Cohen

et al. 2015

Artificial Intelligence

View full text Add to dashboard Cite

Building an intelligent agent that simulates human learning of math and science could potentially benefit both cognitive science, by contributing to the understanding of human learning, and artificial intelligence, by advancing the goal of creating human-level intelligence. However, constructing such a learning agent currently requires manual encoding of prior domain knowledge; in addition to being a poor model of human acquisition of prior knowledge, manual knowledge-encoding is both time-consuming and error-prone. Previous research has shown that one of the key factors that differentiates experts and novices is their different representations of knowledge. Experts view the world in terms of deep functional features, while novices view it in terms of shallow perceptual features. Moreover, since the performance of learning algorithms is sensitive to representation, the deep features are also important in achieving effective machine learning.In this work, we propose an efficient algorithm that acquires representation knowledge in the form of "deep features" for specific domains, and demonstrate its effectiveness in the domain of algebra as well as synthetic domains. We integrate this algorithm into a learning agent, SimStudent, which learns procedural knowledge by observing a tutor solve sample problems, and by getting feedback while actively solving problems on its own. We show that learning representations enhances the generality of the learning agent by reducing the requirements for knowledge engineering. Moreover, we propose an approach that automatically discovers student models using the extended SimStudent. By fitting the discovered model to real student learning curve data, we show that the discovered model is better or as good as human-generated models, and demonstrate how the discovered model may be used to improve a tutoring system's instructional strategy.vi

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Integrating representation learning and skill learning in a human-like intelligent agent

Matsuda

Cohen

et al. 2015

Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Villano [14] first suggested applying Bayesian networks in intelligent tutoring systems. However, Martin and Vanlehn [10] explicitly state that Villano's assessments cannot communicate precisely what a student does not know and cannot identify the components of knowledge that must be taught.…”

Section: Related Workmentioning

confidence: 99%

A Web-Based Intelligent Tutoring System for Computer Programming

Butz

Song

Maguire

IEEE/WIC/ACM International Conference on Web Intelligence (WI'04)

View full text Add to dashboard Cite

show abstract

“…There has been substantial interest in the cognitive science, education, and intelligent tutoring systems communities in modeling and tracking student learning. In particular, there have been a number of results demonstrating the benefit of taking a Bayesian probabilistic approach (see, e.g., [4,6,7,17]). However, there has been much less work on how to compute an automated teaching policy that leverages a probabilistic learner model in order to achieve a long-term teaching objective, which is the focus of this paper.…”

Section: Introductionmentioning

confidence: 99%

Faster Teaching by POMDP Planning

Rafferty

Brunskill

Griffiths

et al. 2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Both human and automated tutors must infer what a student knows and plan future actions to maximize learning. Though substantial research has been done on tracking and modeling student learning, there has been significantly less attention on planning teaching actions and how the assumed student model impacts the resulting plans. We frame the problem of optimally selecting teaching actions using a decision-theoretic approach and show how to formulate teaching as a partially-observable Markov decision process (POMDP) planning problem. We consider three models of student learning and present approximate methods for finding optimal teaching actions given the large state and action spaces that arise in teaching. An experimental evaluation of the resulting policies on a simple concept-learning task shows that framing teacher action planning as a POMDP can accelerate learning relative to baseline performance.

show abstract

Probabilistic student models: Bayesian Belief Networks and Knowledge Space Theory

Cited by 58 publications

References 3 publications

Integrating representation learning and skill learning in a human-like intelligent agent

Integrating representation learning and skill learning in a human-like intelligent agent

A Web-Based Intelligent Tutoring System for Computer Programming

Faster Teaching by POMDP Planning

Contact Info

Product

Resources

About