Radial basis function neural network learning with modified backpropagation algorithm

Abstract

Radial Basis Function Neural Network (RBFNN) is a class of Artificial Neural Network (ANN) widely used in science and engineering for classification problems with Backpropagation (BP) algorithm. However, major disadvantages of BP are due to the relatively slow convergence rate and always being trapped at the local minima. To overcome this problem, an improved Backpropagation (MBP) algorithm using modified cost function was developed to enhance RBFNN learning with discretized data to enhance the performance of classification accuracy and error rate convergence of the network. In RBFNN learning with Standard Backpropagation (SBP), there are many elements to be considered such as the number of input nodes, number of hidden nodes, number of output nodes, learning rate, bias rate, minimum error and activation functions. These parameters affect the speed of RBFNN learning. In this study, the proposed MBP algorithm was applied to RBFNN to enhance the learning process in terms of classification accuracy and error rate convergence. The performance measurement was conducted by comparing the results of MBP-RBFNN with SBP-RBFNN using five continuous and five discretized dataset with ROSETTA tool kit. Two programs have been developed: MBP-RBFNN and SBP-RBFN. The results show that MBP-RBFNN gave the better results in terms of classification accuracy and error rate compared to SBP-RBFNN, together with statistical test to verify the significance of the results on the classification accuracy.