Learn++ algoritmasi ile destek vektör makineleri siniflayicilar topluluǧunun oluşturulmasi

Translated title of the contribution: Ensemble of support vector machines classifiers with Learn++ algorithm

Zeki Erdem, Robi Polikar, Nejat Yumuşak, Fikret Gürgen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In the recent years, Support Vector machines (SVMs) classifiers have been successfully applied to solve a large number of problems. Since SVMs use the global learning technique it suffers from the catastrophic forgetting phenomenon (also called unlearning) which is the inability of the system to learn new patterns without forgetting previously learned ones. Learn++ have been recently introduced as an incremental learning algorithm capable of learning additional data that may later become available. To deal with the catastrophic forgetting problem and to add the incremental learning capability to SVMs classifiers, we propose to use the SVM ensemble with Learn++. Various simulation results for three real world applications that the proposed SVM ensemble show promising results.

Translated title of the contributionEnsemble of support vector machines classifiers with Learn++ algorithm
Original languageTurkish
Title of host publicationProceedings of the IEEE 13th Signal Processing and Communications Applications Conference, SIU 2005
Pages687-690
Number of pages4
DOIs
StatePublished - Dec 1 2005
EventIEEE 13th Signal Processing and Communications Applications Conference, SIU 2005 - Kayseri, Turkey
Duration: May 16 2005May 18 2005

Publication series

NameProceedings of the IEEE 13th Signal Processing and Communications Applications Conference, SIU 2005
Volume2005

Other

OtherIEEE 13th Signal Processing and Communications Applications Conference, SIU 2005
CountryTurkey
CityKayseri
Period5/16/055/18/05

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'Ensemble of support vector machines classifiers with Learn++ algorithm'. Together they form a unique fingerprint.

Cite this