MLP-RBF: A Cooperative Multi-Modular Neural Network Application in High-Energy Physics

Abstract

A cooperative multi-modular neural network architecture ispresented: a Multi-Layer Perceptron (MLP), followed by aRadial Basis Function network (RBF). It is shown that, inthe LEP experiment of electron-positron collision run atCERN, this architecture was able to outperform both asimple multi-layer perceptron, a multi-modular MLP+LVQ(LVQ: Learning Vector Quantization) and MLP+RBF trainedsequentially and a conventional technique (DiscriminantAnalysis). (author). 10 refs., 2 figs. (Atomindex citation25:073617)