A Study on Information Granular-Driven Polynomial Neural Networks

In this study, we introduce a new design methodology of information granular-driven polynomial neural networks (IgPNNs) that is based on multi-layer perceptron with Context-based Polynomial Neurons (CPNs) or Polynomial Neurons (PNs). Our main objective is to develop a methodological design strategy of IgPNNs as follows: (a) The 1st layer of the proposed network consists of Context-based Polynomial Neuron (CPN). In here, CPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Context- based Fuzzy C-Means (C-FCM) clustering method. The context-based clustering supporting the design of information granules is completed in the space of the input data while the build of the clusters is guided by a collection of some predefined fuzzy sets defined in the output space. (b) The proposed design procedure being applied at each layer of IgPNN leads to the selection of preferred nodes of the network (CPNs or PNs) whose local characteristics can be easily adjusted. These options contribute to the flexibility as well as simplicity and compactness of the resulting architecture of the network. For the evaluation of performance of the proposed IgPNNs, we describe a detailed characteristic of the proposed model using a well-known learning machine data.