Optimization of Mixed Pooling Using Genetic Algorithm for Convolutional Neural Networks

Basit Öğe Kaydı
dc.contributor.authorGürkahraman, Kali
dc.contributor.authorKarakiş, Rukiye
dc.date.accessioned2024-10-26T17:51:08Z
dc.date.available2024-10-26T17:51:08Z
dc.date.issued2024
dc.departmentSivas Cumhuriyet Üniversitesi
dc.descriptionBerdan Civata B.C.; et al.; Figes; Koluman; Loodos; Tarsus University
dc.description32nd IEEE Conference on Signal Processing and Communications Applications, SIU 2024 -- 15 May 2024 through 18 May 2024 -- Mersin -- 201235
dc.description.abstractTwo of the most commonly used pooling methods in Convolutional Neural Networks are maximum and average pooling. The maximum pooling method may lead to the loss or reduction of discriminative features in high-intensity inputs. On the other hand, in the average pooling method, when average values calculated from local regions are of low intensity, it can cause a decrease in the contrast of feature maps. Therefore, it has been observed that the hybrid pooling method, which weights and combines the outputs of both methods, performs better in some applications. In this study, it is demonstrated that the optimal value of the learnable parameter used for weighting may not be found when updated with all model parameters during the training process. To address this issue, the weighting in hybrid pooling is optimized independently from the model using a Genetic Algorithm (GA). In a multi-classification study conducted with the Flowers dataset, the performance of multi-classification obtained through GA optimization was found to be higher compared to the traditionally learned weight model, based on test results. The accuracy values of the model optimized with GA and the models containing traditionally learned weight were found to be 0.8299 and 0.8109, respectively. © 2024 IEEE.
dc.identifier.doi10.1109/SIU61531.2024.10601152
dc.identifier.isbn979-835038896-1
dc.identifier.scopus2-s2.0-85200835018
dc.identifier.urihttps://doi.org/10.1109/SIU61531.2024.10601152
dc.identifier.urihttps://hdl.handle.net/20.500.12418/26048
dc.identifier.wosWOS:001297894700338
dc.indekslendigikaynakScopus
dc.language.isotr
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof32nd IEEE Conference on Signal Processing and Communications Applications, SIU 2024 - Proceedings
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectaverage pooling; genetic algorithm; maximum pooling; mixed pooling; optimization
dc.titleOptimization of Mixed Pooling Using Genetic Algorithm for Convolutional Neural Networks
dc.title.alternativeEvrişimli Sinir Ağları için Genetik Algoritma Kullanılarak Karma Havuzlamanın Optimizasyonu
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu