Files in this item



application/pdf9010819.pdf (7MB)Restricted to U of Illinois
(no description provided)PDF


Title:Learning companion systems
Author(s):Chan, Tak-Wai
Doctoral Committee Chair(s):Baskin, Arthur B., III
Department / Program:Computer Science
Discipline:Computer Science
Degree Granting Institution:University of Illinois at Urbana-Champaign
Subject(s):Education, Mathematics
Artificial Intelligence
Computer Science
Abstract:This thesis describes a new class of Intelligent Tutoring Systems (ITS) which I call the Learning Companion Systems (LCS). In the learning environment of such a system, there are three agents involved, namely, the human student, the computer learning companion, and the computer teacher. As implied by its name, the role of the computer learning companion is to act as a learning companion for the student. To this end, the companion performs the learning task at about the same level as the student, and both the student and the companion exchange ideas while being presented the same material by the teacher. In designing the prototype of LCS, Integration-Kid, in the domain of integration, I define some protocols of learning activities among the three agents. These protocols reflect the different learning stages of the learners in the learning process as well as appropriately restrict their possible unbounded interactions. Curriculum Tree, an architecture based on the domain structure is designed as the implementation framework of Integration-Kid. Production systems are used to simulate different agents' interactions via a common blackboard. The basis of the problem solver for both the companion and the teacher is a term rewriting system. Finally, the disadvantages of my design of the prototype and LCS in general, and the future directions of LCS related research are discussed.
Issue Date:1989
Rights Information:Copyright 1989 Chan, Tak-Wai
Date Available in IDEALS:2011-05-07
Identifier in Online Catalog:AAI9010819
OCLC Identifier:(UMI)AAI9010819

This item appears in the following Collection(s)

Item Statistics