Knowledge Representation in Intelligent Educational Systems

Abstract

In this chapter, we deal with knowledge representation in Intelligent Educational Systems (IESs). We make an effort to define requirements for Knowledge Representation (KR) in an IES. The requirements concern all stages of an IES’s life cycle (construction, operation, and maintenance), all types of users (experts, engineers, learners) and all its modules (domain knowledge, user model, pedagogical model). We also briefly present various KR schemes, focusing on neurules, a kind of hybrid rules integrating symbolic rules and nuerocomputing. We then compare all of them as far as the specified KR requirements are concerned. It appears that various hybrid approaches to knowledge representation can satisfy the requirements in a greater degree than that of single representations. Another finding is that there is not a hybrid scheme that can satisfythe requirements of all the modules of an IES. So, multiple representations or a multi-paradigm representation environment could provide a solution to requirements satisfaction.