Modular neural network architecture using piece-wise linear mapping
S. Subbarayan, K.K. Kim, MICHAEL T. MANRY, Venkat Devarajan, Hung-Han Chen · 2002
A new modular neural network for functional mapping is presented. A training algorithm for the network is presented which employs a clustering method, a weighted distance measure, and the deign of simple modules. Since the individual modules are linear, the network implements a piece-wise linear mapping. The efficiency of this structure in terms of training time and pattern storage capacity is discussed and the results of comparative performances with the multilayer preceptron, is presented. Examples are provided to verify the properties of the modular network.