A Probabilistic Model for the Cooperative Modular Neural Network

Abstract. This paper presents a model for the probability of correct classification for the Cooperative Modular Neural Network (CMNN). The model enables the estimation of the performance of the CMNN using parameters obtained from the data set. The performance estimates for the experiments presented are quite accurate (less than 1% relative difference). We compare the CMNN with a multilayer perceptron with equal number of weights and conclude that the CMNN is preferred for complex problems. We also investigate the error introduced by one of the CMNN voting strategies.

• Type: Conference
• Year: 2003
• Where: IBPRIA
• Authors: Luís A. Alexandre, Aurélio C. Campilho, Mohamed S. Kamel
• Keywords: CMNN Voting Strategies, IBPRIA 2003, Image Analysis, Modular Neural Network, Multilayer Perceptron