Accession Number : ADA262796


Title :   Modeling Student Knowledge with Self-Organizing Feature Maps


Descriptive Note : Final technical rept. Feb 1991-Apr 1992


Corporate Author : HONEYWELL SENSOR AND SYSTEM DEVELOPMENT CENTER MINNEAPOLIS MN


Personal Author(s) : Harp, Steven A ; Samad, Tariq ; Villano, Michael


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a262796.pdf


Report Date : Mar 1993


Pagination or Media Count : 28


Abstract : This report describes a novel application of neural networks to model the behavior of students in the context of an intelligent tutoring system. Self- organizing feature maps are used to capture the possible states of student knowledge from an existing test database. The trained network implements a universal student knowledge model that is compatible with recently developed Knowledge Space Theory approaches to student assessment and computer aided instruction. The student model can be applied to rapidly assess the knowledge of any given student, and chart a path from lower to higher states of expertise. We illustrate the concept on an aircraft fuel management domain, demonstrating its noise-tolerance and insensitivity to feature map parameter values. An approach to determining the correct feature map size is also described.


Descriptors :   *BEHAVIOR , *COMPUTER AIDED INSTRUCTION , TEST AND EVALUATION , DATA BASES , NEURAL NETS , AIRCRAFT , MANAGEMENT , MODELS , STUDENTS , NETWORKS , TOLERANCES(PHYSIOLOGY) , INSTRUCTIONS , CHARTS , NOISE , VALUE , COMPUTERS , PARAMETERS , THEORY , TEACHING METHODS , PATHS , FUELS , MAPS


Subject Categories : Humanities and History
      Psychology


Distribution Statement : APPROVED FOR PUBLIC RELEASE