Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο: https://hdl.handle.net/20.500.14279/2481
Πεδίο DCΤιμήΓλώσσα
dc.contributor.authorKasparis, Takis-
dc.contributor.authorGeorgiopoulos, Michael N.-
dc.contributor.authorKoufakou, Anna-
dc.contributor.otherΚασπαρής, Τάκης-
dc.date.accessioned2013-02-15T14:19:53Zen
dc.date.accessioned2013-05-17T05:30:10Z-
dc.date.accessioned2015-12-02T11:26:57Z-
dc.date.available2013-02-15T14:19:53Zen
dc.date.available2013-05-17T05:30:10Z-
dc.date.available2015-12-02T11:26:57Z-
dc.date.issued2001-03-21-
dc.identifier.citationProceedings Volume 4390, Applications and Science of Computational Intelligence IV; (2001), Orlando, Floridaen_US
dc.identifier.issn0277-786X-
dc.description.abstractIn this paper we are examining the issue of overtraining in Fuzzy ARTMAP. Over-training in Fuzzy ARTMAP manifests itself in two different ways: (a) it degrades the generalization performance of Fuzzy ARTMAP as training progresses, and (b) it creates unnecessarily large Fuzzy ARTMAP neural network architectures. In this work we are demonstrating that overtraining happens in Fuzzy ARTMAP and we propose an old remedy for its cure: crossvalidation. In our experiments we compare the performance of Fuzzy ARTMAP that is trained (i) until the completion of training, (ii) for one epoch, and (iii) until its performance on a validation set is maximized. The experiments were performed on artificial and real databases. The conclusion derived from these experiments is that cross-validation is a useful procedure in Fuzzy ARTMAP, because it produces smaller Fuzzy ARTMAP architectures with improved generalization performance. The trade-off is that cross-validation introduces additional computational complexity in the training phase of Fuzzy ARTMAP.en_US
dc.formatpdfen_US
dc.language.isoenen_US
dc.rights© 2001 SPIEen_US
dc.subjectNeural networksen_US
dc.subjectClassificationen_US
dc.subjectDatabasesen_US
dc.titleCross-validation in fuzzy ARTMAP neural networks for large sample classification problemsen_US
dc.typeConference Papersen_US
dc.affiliationUniversity of Central Floridaen
dc.collaborationUniversity of Central Floridaen_US
dc.subject.categoryElectrical Engineering - Electronic Engineering - Information Engineeringen_US
dc.countryUnited Statesen_US
dc.subject.fieldEngineering and Technologyen_US
dc.publicationPeer Revieweden_US
dc.relation.conferenceSPIE Conference Proceedingsen_US
dc.identifier.doi10.1117/12.421155en_US
dc.dept.handle123456789/54en
cut.common.academicyear2000-2001en_US
item.fulltextNo Fulltext-
item.languageiso639-1en-
item.grantfulltextnone-
item.openairecristypehttp://purl.org/coar/resource_type/c_c94f-
item.cerifentitytypePublications-
item.openairetypeconferenceObject-
crisitem.author.deptDepartment of Electrical Engineering, Computer Engineering and Informatics-
crisitem.author.facultyFaculty of Engineering and Technology-
crisitem.author.orcid0000-0003-3486-538x-
crisitem.author.parentorgFaculty of Engineering and Technology-
Εμφανίζεται στις συλλογές:Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation
CORE Recommender
Δείξε τη σύντομη περιγραφή του τεκμηρίου

SCOPUSTM   
Citations 50

1
checked on 6 Νοε 2023

Page view(s) 50

427
Last Week
0
Last month
28
checked on 13 Μαρ 2025

Google ScholarTM

Check

Altmetric


Όλα τα τεκμήρια του δικτυακού τόπου προστατεύονται από πνευματικά δικαιώματα