Convolutional Fuzzy Neural Networks With Random Weights for Image Classification

dc.authoridZhu, Jihua/0000-0002-3081-8781
dc.authoridWang, Jun/0000-0001-9548-0411
dc.authorwosidWang, Jun/D-6393-2017
dc.contributor.authorWang, Yifan
dc.contributor.authorIshibuchi, Hisao
dc.contributor.authorPedrycz, Witold
dc.contributor.authorZhu, Jihua
dc.contributor.authorCao, Xiangyong
dc.contributor.authorWang, Jun
dc.date.accessioned2024-05-19T14:40:45Z
dc.date.available2024-05-19T14:40:45Z
dc.date.issued2024
dc.departmentİstinye Üniversitesien_US
dc.description.abstractDeep fuzzy neural networks have established a fundamental connection between fuzzy systems and deep learning networks, serving as a crucial bridge between two research fields in computational intelligence. These hybrid networks have powerful learning capability stemming from deep neural networks while leveraging the advantages of fuzzy systems, such as robustness. Due to these benefits, deep fuzzy neural networks have recently been an emerging topic in computational intelligence. With the help of deep learning, fuzzy systems have achieved great performance on the classification task. Although fuzzy systems have been extensively investigated, they still struggle in terms of image classification. In this paper, we propose a convolutional fuzzy neural network that combines improved convolutional neural networks with a fuzzy-set-based fusion technique. Different from convolutional neural networks, filters are randomly generated in convolutional layers in our model. This operation not only leads to the fast learning of the model but also avoids some notorious problems of gradient descent procedures in conventional deep learning methods. Extensive experiments demonstrate that the proposed approach is competitive with state-of-the-art fuzzy models and deep learning models. Compared to classical deep models that require massive training data, the proposed approach works well on small datasets.en_US
dc.description.sponsorshipNational Natural Science Foundation of Chinaen_US
dc.description.sponsorshipNo Statement Availableen_US
dc.identifier.doi10.1109/TETCI.2024.3375019
dc.identifier.issn2471-285X
dc.identifier.urihttps://doi.org10.1109/TETCI.2024.3375019
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5010
dc.identifier.wosWOS:001189479300001en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.language.isoenen_US
dc.publisherIeee-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Transactions on Emerging Topics In Computational Intelligenceen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectDeep Learningen_US
dc.subjectData Modelsen_US
dc.subjectCorrelationen_US
dc.subjectDeep Fuzzy Neural Networksen_US
dc.subjectImage Classificationen_US
dc.subjectConvolutional Neural Networksen_US
dc.titleConvolutional Fuzzy Neural Networks With Random Weights for Image Classificationen_US
dc.typeArticleen_US

Dosyalar