Towards Hebbian learning of Fuzzy Cognitive Maps in pattern classification problems

G. A. Papakostas, D. E. Koulouriotis, A. S. Polydoros, V. D. Tourassis

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

A detailed comparative analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) operating as pattern classifiers, is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM classifier so it equilibrates to a desired state (class mapping). For these purposes, six different types of Hebbian learning algorithms from the literature have been selected and studied in this work. Along with the theoretical description of these algorithms and the analysis of their performance in classifying known patterns, a sensitivity analysis of the applied classification scheme, regarding some configuration parameters have taken place. It is worth noting that the algorithms are studied in a comparative fashion, under common configurations for several benchmark pattern classification datasets, by resulting to useful conclusions about their training capabilities.

Original languageEnglish
Pages (from-to)10620-10629
Number of pages10
JournalExpert Systems with Applications
Volume39
Issue number12
DOIs
Publication statusPublished - Sep 15 2012
Externally publishedYes

Fingerprint

Pattern recognition
Learning algorithms
Classifiers
Sensitivity analysis

Keywords

  • Classifier
  • Fuzzy Cognitive Maps
  • Hebbian learning
  • Pattern classification
  • Soft computing
  • Training

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Engineering(all)

Cite this

Towards Hebbian learning of Fuzzy Cognitive Maps in pattern classification problems. / Papakostas, G. A.; Koulouriotis, D. E.; Polydoros, A. S.; Tourassis, V. D.

In: Expert Systems with Applications, Vol. 39, No. 12, 15.09.2012, p. 10620-10629.

Research output: Contribution to journalArticle

Papakostas, G. A. ; Koulouriotis, D. E. ; Polydoros, A. S. ; Tourassis, V. D. / Towards Hebbian learning of Fuzzy Cognitive Maps in pattern classification problems. In: Expert Systems with Applications. 2012 ; Vol. 39, No. 12. pp. 10620-10629.
@article{31a8950f8a8849299a3cda0a7c41bd71,
title = "Towards Hebbian learning of Fuzzy Cognitive Maps in pattern classification problems",
abstract = "A detailed comparative analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) operating as pattern classifiers, is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM classifier so it equilibrates to a desired state (class mapping). For these purposes, six different types of Hebbian learning algorithms from the literature have been selected and studied in this work. Along with the theoretical description of these algorithms and the analysis of their performance in classifying known patterns, a sensitivity analysis of the applied classification scheme, regarding some configuration parameters have taken place. It is worth noting that the algorithms are studied in a comparative fashion, under common configurations for several benchmark pattern classification datasets, by resulting to useful conclusions about their training capabilities.",
keywords = "Classifier, Fuzzy Cognitive Maps, Hebbian learning, Pattern classification, Soft computing, Training",
author = "Papakostas, {G. A.} and Koulouriotis, {D. E.} and Polydoros, {A. S.} and Tourassis, {V. D.}",
year = "2012",
month = "9",
day = "15",
doi = "10.1016/j.eswa.2012.02.148",
language = "English",
volume = "39",
pages = "10620--10629",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",
number = "12",

}

TY - JOUR

T1 - Towards Hebbian learning of Fuzzy Cognitive Maps in pattern classification problems

AU - Papakostas, G. A.

AU - Koulouriotis, D. E.

AU - Polydoros, A. S.

AU - Tourassis, V. D.

PY - 2012/9/15

Y1 - 2012/9/15

N2 - A detailed comparative analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) operating as pattern classifiers, is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM classifier so it equilibrates to a desired state (class mapping). For these purposes, six different types of Hebbian learning algorithms from the literature have been selected and studied in this work. Along with the theoretical description of these algorithms and the analysis of their performance in classifying known patterns, a sensitivity analysis of the applied classification scheme, regarding some configuration parameters have taken place. It is worth noting that the algorithms are studied in a comparative fashion, under common configurations for several benchmark pattern classification datasets, by resulting to useful conclusions about their training capabilities.

AB - A detailed comparative analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) operating as pattern classifiers, is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM classifier so it equilibrates to a desired state (class mapping). For these purposes, six different types of Hebbian learning algorithms from the literature have been selected and studied in this work. Along with the theoretical description of these algorithms and the analysis of their performance in classifying known patterns, a sensitivity analysis of the applied classification scheme, regarding some configuration parameters have taken place. It is worth noting that the algorithms are studied in a comparative fashion, under common configurations for several benchmark pattern classification datasets, by resulting to useful conclusions about their training capabilities.

KW - Classifier

KW - Fuzzy Cognitive Maps

KW - Hebbian learning

KW - Pattern classification

KW - Soft computing

KW - Training

UR - http://www.scopus.com/inward/record.url?scp=84861193823&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84861193823&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2012.02.148

DO - 10.1016/j.eswa.2012.02.148

M3 - Article

VL - 39

SP - 10620

EP - 10629

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 12

ER -