CMNN: Cooperative modular neural networks

A new cooperative modular neural network (CMNN) architecture for classification is introduced. The main idea is to decrease partial over- and under-learning by dealing with different levels of overlap in separate modules. Motivated by some basic biological modular-networks' concepts, CMNN proposes a new cooperation scheme to integrate the information available at its modules. Cooperative modules utilize some voting techniques to come up with a collective decision. Moreover, the specialization concept is proposed as a solution for high overlap regions in the input space. A number of experiments which assess CMNN's capabilities are outlined. The experiments compare it to several non-modular and modular state-of-the-art alternatives using several benchmark problems. The proposed modularization scheme proves to be an effective way to deal with the complexities of real classification problems. (C) 1998 Published by Elsevier Science B.V. All rights reserved.