A Connectionist Approach for Supporting Personalized Learning in a Web-Based Learning Environment

The paper investigates the use of computational intelligence for adaptive lesson presentation in a Web-based learning environment. A specialized connectionist architecture is developed and a formulation of the planning strategy retrieval in the context of the network dynamics is proposed to select the content of the lesson in a goal-oriented way of 'teaching'. The educational material of the course is stored in a connectionist-based distributed information storage system that provides capabilities for optimal selection of the educational material according to the knowledge needs, abilities and preferences of each learner. Low-level tests of the system have been performed to investigate how the connectionist architecture and the learner model function together to create an operational learning environment. Preliminary experiments indicate that personalized content delivery is provided in an educational effective way.