USING MULTITHRESHOLD QUADRATIC SIGMOIDAL NEURONS TO IMPROVE CLASSIFICATION CAPABILITY OF MULTILAYER PERCEPTRONS

Abstract

This letter proposes a new type of neurons called multithreshold quadratic sigmoidal neurons to improve the classification capability of muitilayer neural networks. In cooperation with single-threshold quadratic sigmoidal neurons, the multithreshold quadratic sigmoidal neurons can be used to improve the classification capability of multilayer neural networks by a factor of four compared to committee machines and by a factor of two compared to the conventional sigmoidal multilayer perceptrons.