Abstract

In this paper we study the effect of the number of training samples for feed forward neural networks (FFNN) which is necessary for training process of feed forward neural network. Also we design 5 FFNN's and train 41 FFNN's which illustrate how good the training samples represent the actual function for FFNN

The article was added to IASJ on 2012-06-13

415 Total full text downloads since the date of addition