Granular transfer learning

Basit Öğe Kaydı
dc.authorscopusidWitold Pedrycz / 58861905800
dc.authorwosidWitold Pedrycz / HJZ-2779-2023
dc.contributor.authorAl-Hmouz, Rami
dc.contributor.authorPedrycz, Witold
dc.contributor.authorAwadallah, Medhat
dc.contributor.authorAmmari, Ahmed
dc.date.accessioned2025-04-18T10:15:19Z
dc.date.available2025-04-18T10:15:19Z
dc.date.issued2024
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractTransfer learning is aimed at supporting the design of machine learning models in the target domain Dt, given that the knowledge (model) has already been constructed in the source domain Ds. The domains Dtand Ds (as well as the corresponding tasks Ts and Tt) are similar, yet not identical. As a result, the model transferred from Ds to Dtin this new environment exhibits its relevance (credibility) only to some limited extent. In this study, we develop an original approach, where we advocate that the knowledge transfer (model transfer) gives rise to a granular model where the level of information granularity associated with the produced results quantifies the relevance (quality or credibility) of the transferred model. In other words, we stress that the quality of knowledge transferred to Dtbecomes captured through a granular generalization of the original numeric model. The overall systematic design process is elaborated on by focusing on the development process of granular neural networks carried out on a basis of the numeric neural networks coming from Ds. The key aspect of the design is to elevate the existing numeric neural network to its granular counterpart by admitting that the connections of the developed model come in the form of information granules, in particular intervals and fuzzy sets. The optimization process is guided by adjusting (optimizing) the level of information granularity being regarded as an essential design asset. The optimized performance index builds upon the descriptors of information granules commonly encountered in Granular Computing. In particular, coverage and specificity measures are treated as sound performance indicators of the quality of knowledge transfer (viz. the performance of the granular neural network expressed in the target domain). Several illustrative examples are provided to visualize the performance of the established design environment.
dc.description.sponsorshipSultan Qaboos University
dc.identifier.citationAl-Hmouz, R., Pedrycz, W., Awadallah, M., & Ammari, A. (2024). Granular transfer learning. Neurocomputing, 600, 128126.
dc.identifier.doi10.1016/j.neucom.2024.128126
dc.identifier.endpage11
dc.identifier.issn0925-2312
dc.identifier.issn1872-8286
dc.identifier.scopus2-s2.0-85198031683
dc.identifier.scopusqualityQ1
dc.identifier.startpage1
dc.identifier.urihttp://dx.doi.org/10.1016/j.neucom.2024.128126
dc.identifier.urihttps://hdl.handle.net/20.500.12713/7007
dc.identifier.volume600
dc.identifier.wosWOS:001267385100001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorPedrycz, Witold
dc.institutionauthoridWitold Pedrycz / 0000-0002-9335-9930
dc.language.isoen
dc.publisherElsevier
dc.relation.ispartofNeurocomputing
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectTransfer Learning
dc.subjectGranular Neural Networks
dc.subjectNeural Networks
dc.subjectGranular Computing
dc.subjectPerformance Analysis
dc.subjectCoverage and Specificity of Information Granule
dc.subjectGranular Parameters
dc.subjectFuzzy Sets
dc.subjectInterval Analysis
dc.subjectAcceptance Criterion
dc.titleGranular transfer learning
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
1-s2.0-S092523122400897X-main.pdf
Boyut:
1.64 MB
Biçim:
Adobe Portable Document Format
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Makale Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu