Towards a model of multi-agent connectionist hybrid system

A connectionist system that is capable of reasoning about problems posed usually to expert systems is used for the purpose of dynamic cognition tasks. The architecture of such a system must contain “classical” AI representations and symbolic information processing entities. Coupling this part of the system with multiple connectionist structures implies a definition for the intercommunication channels, and a specification of the dynamic behavior of the entire system. Some experiments and results are illustrated in an attempt to shed light on the questions raised and the difficulties encountered. The study concludes by contrasting the ideas presented with the mainstream of computational cognitive science