The Performance of the Neocognitron with Various S-Cell and C-Cell Transfer Functions

When a neural network solution to a problem (e.g. handwritten character recognition) is proposed, it is important to know if the structure of the network and the function of the component neurons are well suited to the task. Recent research has examined the structure of Fukushima's neocognitron and the eeect that it has on the classiication of distorted input patterns. We present results which assess the classiication performance of the neocognitron when the function of the component neurons is altered. The tests we describe demonstrate that using S-cells with a sigmoidal transfer function and modiied activation function signiicantly enhances the classiication performance of the neocognitron.