CoMeT | <%=title %>
Collaborative Management of Talks Hello! sign in or register
Bookmark Talks, Share with Friends, and We Recommend More!
Advanced Search
Talk Detail
Posted: wab23 on  Jul 31 11:41:29 AM
Title: A Spectral Learning Approach to Knowledge Tracing  
Mohammad Hassan Falakmasir
Intelligent Systems Program
Sponsor: University of Pittsburgh  >  School of Computing and Information  >  Intelligent Systems Program
Series: ISP Colloquium Series
Date: Sep 06, 2013 12:30 PM - 1:00 PM
Location: Sennott Square - Seminar Room 5317
Groups Posted: Data Science Intelligent Systems Program Learning Technologies 
Bookmarked by:  Yun Huang Roya Hosseini Jidapa K.


Bayesian Knowledge Tracing (BKT) is a common way of determining student knowledge of skills in adaptive educational systems and cognitive tutors. The basic BKT is a Hidden Markov Model (HMM) that models student knowledge based on five parameters: prior, learn rate, forget, guess, and slip. Expectation Maximization (EM) is often used to learn these parameters from training data. However, EM is a time-consuming process, and is prone to converging to erroneous, implausible local optima depending on the initial values of the BKT parameters. In this paper we address these two problems by using spectral learning to learn a Predictive State Representation (PSR) that represents the BKT HMM. We then use a heuristic to extract the BKT parameters from the learned PSR using basic matrix operations. The spectral learning method is based on an approximate factorization of the estimated covariance of windows from students’ sequences of correct and incorrect responses; it is fast, local-optimum-free, and statistically consistent. In the past few years, spectral techniques have been used on real-world problems involving latent variables in dynamical systems, computer vision, and natural language processing. Our results suggest that the parameters learned by the spectral algorithm can replace the parameters learned by EM; the results of our study show that the spectral algorithm can improve knowledge tracing parameter-fitting time significantly while maintaining the same prediction accuracy, or help to improve accuracy while still keeping parameter-fitting time equivalent to EM.

People Who Bookmarked This Talk, Also Bookmarked
RSS Feed: RSS 2.0
ATOM Feed: Atom
iCalendar: iCal
Share: Bookmark and Share
Google Calendar:
CoMeT Blog
©2009-2022 CoMeT - Supported by Google Grant
School of Information Sciences, University of Pittsburgh, 135 North Bellefield Avenue, Pittsburgh, PA 15260