Uniwersytet Warszawski Ltf-c: Architecture, Training Algorithm and Applications of New Neural Classier

This paper presents a new model of an arti cial neural network solving classi cation problems, called Local Transfer Function Classi er (LTF-C). Its architecture is very similar to this of the Radial Basis Function neural network (RBF), however it utilizes an entirely di erent learning algorithm. This algorithm is composed of four main parts: changing positions of reception elds, changing their sizes, insertion of new hidden neurons and removal of unnecessary ones during the training. The paper presents also results of LTF-C application to three real-life tasks: handwritten digit recognition, credit approval and cancer diagnosis. LTF-C was able to solve each of these problems with better accuracy than most popular classi cation systems. Moreover, LTF-C was relatively small and fast.