A Rotated Kernel Probabilistic Neural Network (RKPNN) for Multi-class Classification

Abstract

An improvement to the Probabilistic Neural Network (PNN) is presented that overcomes two weaknesses of the original model. In the new model, due to the fact that each neuron uses its own Gaussian kernel function, a better generalization ability is achieved by the means of stretching and rotation leading to the Rotated Kernel Probabilistic Neural Network (RKPNN). Furthermore, an algorithm is presented that calculates automatically the kernel parameters of each Gaussian function. The covariance matrices will be subdivided into two other matrices R and S that are calculated separately. This training is slower than that of the original PNN, but in its complexity comparable with other classification methods. A real-world example finally prooves that the proposed model shows good generalization capacity with similar or even slightly better results than other approaches.