An incremental representation of conceptual symbols using RCE neural network

This paper presents the application of an RCE (restricted Coulomb energy) neural network for the development of an incremental representation of conceptual symbols. We first briefly discuss the issue of the autonomous learning mechanism within the context of self-development of perceptive and cognitive skills through interaction with a real environment. Then we address the issue of internal representations of knowledge and skills. As an example, we illustrate in detail the application and implementation of an RCE neural network to incrementally build an internal representation of conceptual symbols at an elementary level (e.g. the symbols from 0 to 9, or from a to z).