Property of Artificial Neural Networks of Classification with respect to Training Set Size

Multilayer perceptrons and radial basis function networks are used most often in classification tasks, even though the two neural networks have different performance in classification tasks depending on the available training data sets. This paper shows the accuracy change in classification of the two neural networks when training data set size changes. Experiments were run with four data sets and found that multilayer perceptrons show relatively better accuracies as the training data set size grows, while radial basis function networks do not improve much compared to the other neural networks, as a result the accuracy of multilayer perceptron became better for two data sets, as the training data set size grew. Key-Words: artificial neural networks, the size of training data, prediction accuracy