This paper proposes a neural network approach for the handling of disjunctive fuzzy information in the feature space. This neural network model consists of two types of nodes in the hidden layer. The prototype nodes and the exemplar nodes represent cluster centroids and exceptions in the feature space, respectively. This classifier can automatically generate and refine prototypes for distinct clusters in the feature space. The prototypes will form near-optimal decision regions to meet the distribution of input patterns and classify as many input patterns as possible. Next, exemplars will be created and expanded to learn the patterns that cannot be classified by the prototypes. Such a training strategy can reduce the memory requirement and speed up the process of nonlinear classification. In addition, on-line learning is supplied in this classifier and the computational load is lightened.