A variable node-to-node-link neural network and its application to hand-written recognition

Abstract

This paper presents a variable node-to-node-link neural network (VN²NN) trained by real-coded genetic algorithm (RCGA). The VN²NN exhibits a node-to-node relationship in the hidden layer, and the network parameters are variable. These characteristics make the network adapt to the changes of the input environment, enable it to tackle different input sets distributed in a large domain. Each input data set is effectively handled by a corresponding set of network parameters. The set of parameters are governed by the other nodes. Taking the advantage of these features, the proposed network ensures better learning and generalization abilities. Application of the proposed network to hand-written graffiti recognition will be presented so as to illustrate the improvement.