Analysis and test of efficient methods for building recursive deterministic perceptron neural networks.

De Montfort University Open Research Archive

Show simple item record

dc.contributor.author Elizondo, David en
dc.contributor.author Birkenhead, Ralph, 1955- en
dc.contributor.author Gongora, Mario Augusto en
dc.contributor.author Luyima, P. en
dc.contributor.author Taillard, Eric
dc.date.accessioned 2008-11-24T13:24:11Z
dc.date.available 2008-11-24T13:24:11Z
dc.date.issued 2007-12-01 en
dc.identifier.citation Elizondo, D.A. et al. (2007) Analysis and test of efficient methods for building recursive deterministic perceptron neural networks. Neural Networks, 20 (10), pp. 1095-1108.
dc.identifier.issn 0893-6080 en
dc.identifier.uri http://hdl.handle.net/2086/175
dc.description This paper introduces a comparison study of three existing methods for building Recursive Deterministic Perceptron Neural Networks. Three methods were compared in terms of their level of generalisation, convergence time and topology sizes. Prior to this study only an exhaustive, NP-Complete method was used for building RDP neural networks. Due to its high complexity, this limited its use in real world classification problems. This work shows that the other two methods, with a polynomial time complexity, can be used as an alternative. These results will widen the use of the RDP neural network. The impact factor is 2.000. en
dc.language.iso en en
dc.publisher Neural Networks en
dc.subject RAE 2008
dc.subject UoA 23 Computer Science and Informatics
dc.subject recursive deterministic perceptron
dc.subject batch learning
dc.subject incremental learning
dc.subject modular learning
dc.subject performance sensitivity analysis
dc.subject convergence time
dc.subject topology
dc.title Analysis and test of efficient methods for building recursive deterministic perceptron neural networks. en
dc.type Article en
dc.identifier.doi http://dx.doi.org/10.1016/J.neunet.2007.07.009 en
dc.researchgroup DIGITS en
dc.researchgroup Centre for Computational Intelligence
dc.peerreviewed Yes


Files in this item

This item appears in the following Collection(s)

Show simple item record