Modeling and Evolutionary Learning of Modular Neural Networks

Modular Neural Networks Qiangfu Zhao The University of Aizu Aizu-Wakamatsu, Fukushima 965-8580, Japan Email: [email protected] Abstract In the last decade, a number of neural network models have been proposed in the literature. Some of them have been successfully incorporated in di erent intelligent information processing systems. Among these models, a group of most successful ones are the modular neural networks (MNNs). This paper introduces a general model of MNNs, and proposes a neural network tree (NNTree) model. An evolutionary algorithm is also given for designing the NNTrees. The usefulness of the NNTrees and the e ectiveness of the learning algorithm are veri ed through experiments with a digit recognition problem.