A shortage of teachers in scientific disciplines, shrinking educational budgets, and larger numbers of students per classroom instructor--all point to the need for increased emphasis on computers in education. Given the power of neural networks and the potential effectiveness of computer-based instructional systems, this research has focused on combining these systems. The results of this dissertation demonstrate the promise of synthesizing neural networks and intelligent tutoring systems (ITS's). / This dissertation discusses two different neural networks: the consistency network and the neural tutor. The consistency network provides an efficient means of dynamically maintaining the consistency of information in ITS's containing a student record. The inferencing process of neural networks furnishes a convenient and natural method of propagating information throughout the student record. / The consistency network assimilates the skill assessment of knowledge components in its inferencing process. This assessment includes the incorporation of historical data and allows for the fuzziness inherent in determining the performance level of students. / The research also investigates the use of neural networks to assist in the difficult and critical task of knowledge acquisition for intelligent systems. Using synthetic data, the network shows promise in learning the weights employed in the consistency network. By starting with a priori information and using a neural network to expand this knowledge, the task of developing intelligent systems can be reduced. / The neural tutor helps determine the appropriate tutoring technique to be used in the presence of student errors. This network demonstrates that neural networks can be used to learn the appropriate class of response to be given the student based on training samples. / Source: Dissertation Abstracts International, Volume: 53-11, Section: B, page: 5828. / Major Professor: Lois Hawkes. / Thesis (Ph.D.)--The Florida State University, 1992.
| Identifer | oai:union.ndltd.org:fsu.edu/oai:fsu.digital.flvc.org:fsu_76817 |
| Contributors | Posey, Chlotia L., Florida State University |
| Source Sets | Florida State University |
| Language | English |
| Detected Language | English |
| Type | Text |
| Format | 141 p. |
| Rights | On campus use only. |
| Relation | Dissertation Abstracts International |
Page generated in 0.0021 seconds