Performance Analysis of Pattern Classification for the Handwritten English Vowels With Back Propagation & DG-RBF Feed Forward Neural Networks

The purpose of this study is to analyze the performance of feed forward neural network for the pattern. classification of hand written English vowels using conventional back propagation algorithm for multi layer feed forward neural network and decent gradient learning for radial basis function network. This analysis has been done with five different samples of hand written English vowels. These characters are presented to the neural network for the training. Adjusting the connection strength and network parameters perform the training process in the neural network. By using a simulator program, each algorithm is compared with five data sets of handwritten English language vowels. The 5 trials indicate the significant difference between the two algorithms for the presented data sets. The results indicate that the performance of the neural network is much efficient and convergence for the RBF network.