Mi DSpace
Usuario
Contraseña
Please use this identifier to cite or link to this item: http://hdl.handle.net/UCSP/15881
Title: Real adaboost with gate controlled fusion
Authors: Mayhua López, Efraín Tito
Gómez Verdejo, Vanessa
Figueiras-Vidal, Anibal
Keywords: Bench-mark problems;Classification performance;Computational effort;Controlled fusion;ensembles;Linear combinations;Mixtures of experts;Training requirement;Benchmarking;Classification (of information);Direct energy conversion;Neural networks;Adaptive boosting
Issue Date: 2012
metadata.dc.relation.uri: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84876902833&doi=10.1109%2fTNNLS.2012.2219318&partnerID=40&md5=efb57382c29fc8be71bdee5d1ad3053b
Abstract: In this brief, we propose to increase the capabilities of standard real AdaBoost (RAB) architectures by replacing their linear combinations with a fusion controlled by a gate with fixed kernels. Experimental results in a series of well-known benchmark problems support the effectiveness of this approach in improving classification performance. Although the need for cross-validation processes obviously leads to higher training requirements and more computational effort, the operation load is never much higher; in many cases it is even lower than that of competitive RAB schemes. © 2012 IEEE.
URI: http://repositorio.ucsp.edu.pe/handle/UCSP/15881
ISSN: 2162237X
Appears in Collections:Artículos de investigación

Files in This Item:
There are no files associated with this item.


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