Effect of varying neurons in the hidden layer of neural network for simple character recognition

Abstract

Numerous advancements, which have been made in the development of intelligent system, are inspired by the biological activities. Neural network is one such complex adaptive system that is able to capture and represent complex input/output relationships. This paper gives an overview of the neural network and further highlights the effect of noise and the number of neurons on the performance of the neural network for simple character recognition application. The number of neurons in the hidden layer is varied during simulation and the effect is observed in the percentage of errors in the recognition of characters