期刊名称：Journal of Intelligent Learning Systems and Applications
印刷版ISSN：2150-8402
电子版ISSN：2150-8410
出版年度：2010
卷号：2
期号：1
页码：1-11
DOI：10.4236/jilsa.2010.21001
出版社：Scientific Research Publishing
摘要：This paper presents a new neural network structure and namely node-to-node-link neural network (N-N-LNN) and it is trained by real-coded genetic algorithm (RCGA) with average-bound crossover and wavelet mutation [1]. The N-N-LNN exhibits a node-to-node relationship in the hidden layer and the network parameters are variable. These characteristics make the network adaptive to the changes of the input environment, enabling it to tackle different input sets distributed in a large domain. Each input data set is effectively handled by a corresponding set of network parame-ters. The set of parameters is governed by other nodes. Thanks to these features, the proposed network exhibits better learning and generalization abilities. Industrial application of the proposed network to hand-written graffiti recognition will be presented to illustrate the merits of the network.
