An Adaptive Classifier Based on Artificial Immune Network.

The central problem in training a radial basis function neural network is the selection of hidden layer neurons, which includes the selection of the center and width of those neurons. In this paper, we propose a new method to construct an adaptive RBF neural network classifier based on artificial immune network algorithm. A multiple granularities immune network (MGIN) algorithm is employed to get the candidate hidden neurons and construct an original RBF network including all candidate neurons, and a removing redundant neurons procedure is used to simplify the classifier finally. Some experimental results show that the network obtained tends to generalize well. [ABSTRACT FROM AUTHOR]