Realization of Generalized RBF Network

Neural classifiers have been widely used in many application areas. This paper describes generalized neural classifier based on the radial basis function network. The contributions of this work are: i) improvement on the standard radial basis function network architecture, ii) proposed a new cost function for classification, iii) hidden units feature subset selection algorithm, and iv) optimizing the neural classifier using the genetic algorithm with a new cost function. Comparative studies on the proposed neural classifier on protein classification problem are given.