Heterogeneous knowledge representation: integrating connectionist and symbolic computations

Abstract

Heterogeneous knowledge representation allows to combine several knowledge represent techniques. For instance connectionist and symbolic systems are two different computational paradigms and knowledge representation tools. Unfortunately, the integration of different paradigms and knowledge representations is not easy and very often is informal. In this paper, we prop ose a formal approach to integrate these two paradigms where as symbolic system we consider a (logic) rule based system. The integration is operated at language level between neural networks and rule languages. The formal mo del that allow the integration is based on constraint logic programming and provide an integrated framework to represent and pro cess heterogeneous knowledge. In order to achieve this we de ne a new language that allow to express and mo del in a natural and intuitive way the above issues together with the operational semantics.