Knowledge based artificial networks networks have been applied quite successfully to propositional knowledge representation and reasoning tasks. However, as soon as these tasks are extended to structured objects and structure-sensitive processes it is not obvious at all how neural symbolic systems should look like such that they are truly connectionist and allow for a declarative reading at the same time. The core method aims at such an integration. It is a method for connectionist model generation using recurrent networks with feed-forward core. After an introduction to the core method, this paper will focus on possible connectionist representations of structured objects and their use in structure-sensitive reasoning tasks.

B. Hammer , P. Hitzler (Pascal)
Studies in computational intelligence
Networks and Optimization

Bader, S., Hitzler, P., Hölldobler, S., & Witzel, A. (2007). The Core Method: Connectionist Model Generation for First-Order Logic Programs. In B. Hammer & P. Hitzler (Eds.), Studies in computational intelligence. Springer.