Please use this identifier to cite or link to this item:
Title: Task decomposition using pattern distributor
Authors: Guan, SU
Neo, T
Bao, C
Keywords: Task decomposition, Multilayered feedforward neural network, Pattern distributor
Issue Date: 2004
Publisher: Freund & Pettman
Citation: Journal of Intelligent Systems, 13(2): 213-150
Abstract: In this paper, we propose a new task decomposition method for multilayered feedforward neural networks, namely Task Decomposition with Pattern Distributor in order to shorten the training time and improve the generalization accuracy of a network under training. This new method uses the combination of modules (small-size feedforward network) in parallel and series, to produce the overall solution for a complex problem. Based on a “divide-and-conquer” technique, the original problem is decomposed into several simpler sub-problems by a pattern distributor module in the network, where each sub-problem is composed of the whole input vector and a fraction of the output vector of the original problem. These sub-problems are then solved by the corresponding groups of modules, where each group of modules is connected in series with the pattern distributor module and the modules in each group are connected in parallel. The design details and implementation of this new method are introduced in this paper. Several benchmark classification problems are used to test this new method. The analysis and experimental results show that this new method could reduce training time and improve generalization accuracy.
ISSN: 0334-1860
Appears in Collections:Electronic and Computer Engineering
Dept of Electronic and Computer Engineering Research Papers

Files in This Item:
File Description SizeFormat 
task_decomp_PD_12-29-03.pdf172.21 kBAdobe PDFView/Open

Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.