Title | Modular neural network task decomposition via entropic clustering |
Publication Type | Conference Paper |
Year of Publication | 2006 |
Authors | Santos, JM, Alexandre, LA, De Sá, JM |
Conference Name | Proceedings - ISDA 2006: Sixth International Conference on Intelligent Systems Design and ApplicationsProc. ISDA Sixth Int. Conf. Intelligent Syst. Design Applic. |
Date Published | 2006/// |
Conference Location | Jinan |
ISBN Number | 0769525288 (ISBN); 9780769525280 (ISBN) |
Keywords | Classification (of information), Clustering algorithms, Decision Theory, Entropic clustering, Learning systems, Modular neural network task decomposition, Monolithic neural networks, Neural networks, Weight coupling |
Abstract | The use of monolithic neural networks (such as a multilayer perceptron) has some drawbacks: e.g. slow learning, weight coupling, the black box effect. These can be alleviated by the use of a modular neural network. The creation of a MNN has three steps: task decomposition, module creation and decision integration. In this paper we propose the use of an entropie clustering algorithm as a way of performing task decomposition. We present experiments on several real world classification problems that show the performance of this approach. © 2006 IEEE. |
URL | http://www.scopus.com/inward/record.url?eid=2-s2.0-34547502901&partnerID=40&md5=c784fc5fb020181d30a63f65ed112c41 |