A color pattern recognition problem based on the multiple classes random neural network model

Abstract

Gelenbe has modeled the neural network using an analogy with the queuing theory. Recently, Fourneau and Gelenbe have proposed an extension of this model, called multiple classes random neural network (RNN) model. The purpose of this paper is to describe the use of the multiple classes RNN model to recognize patterns having different colors. We propose a learning algorithm for the recognition of color patterns based upon the non-linear equations of the multiple classes RNN model using gradient descent of a quadratic error function. In addition, we propose a progressive retrieval process with adaptive threshold value.