Abstract

Abstract—We have recently proposed a novel neural network structure called an Affordable Neural Network (AfNN), in which affordable neurons of the hidden layer are considered as the elements responsible for the robust-ness property as is observed in human brain function. We have confirmed that the AfNN gains good performance both of the generalization ability and the learning ability. In this study, we focus on the firng frequency of neurons in the hidden layer and the amount of weight changes during the learning process. By computer simulations, we confirm that the AfNN generates scale-free properties. 1.