Yayın:
The Performance of Differential Evolution Algorithm for Training CSFNN Using a Pattern Recognition Application

Basit öğe sayfası
dc.contributor.authorYilmaz, Ali Riza
dc.contributor.authorErkmen, Burcu
dc.contributor.authorYavuz, Oguzhan
dc.date.accessioned2026-06-27T13:20:47Z
dc.date.issued2013
dc.description.abstractIn this work, Conic Section Function Neural Network (CSFNN) has been trained by differential evolution algorithm (DEA) to overcome local minimum problems. The classification performance of the CSFNN trained by DEA has been analyzed by using high-dimensional and non-linear signature recognition database. The CSFNN training performance of the DEA has been compared with that of the gradient based back-propagation algorithm (BPA). The simulation results show that the classification performance of the CSFNN trained by DEA is more stable than that of the CSFNN trained by BPA for running several trials.en
dc.identifier.endpage823
dc.identifier.isbn978-1-4673-6249-8; 978-1-4673-6248-1
dc.identifier.startpage820
dc.identifier.urihttps://hdl.handle.net/20.500.14981/52020
dc.identifier.wos000326374300158
dc.language.isoeng
dc.publisherIEEE
dc.relation.conference4th International Conference on Intelligent Control and Information Processing (ICICIP)
dc.relation.ispartofPROCEEDINGS OF THE 2013 FOURTH INTERNATIONAL CONFERENCE ON INTELLIGENT CONTROL AND INFORMATION PROCESSING (ICICIP)
dc.subjectAutomation & Control Systems
dc.subjectComputer Science
dc.subjectEngineering
dc.titleThe Performance of Differential Evolution Algorithm for Training CSFNN Using a Pattern Recognition Application
dc.typeProceedings Paper
dspace.entity.typePublication
local.import.sourceWOS

Dosyalar

Koleksiyonlar

Yayınlar