Training Fuzzy Cognitive Maps by using Hebbian learning algorithms: A comparative study

G. A. Papakostas; Athanasios Polydoros; D. E. Koulouriotis; V. D. Tourassis

doi:10.1109/FUZZY.2011.6007544

Training Fuzzy Cognitive Maps by using Hebbian learning algorithms: A comparative study

G. A. Papakostas^*, Athanasios Polydoros, D. E. Koulouriotis, V. D. Tourassis

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

24 Citations (Scopus)

Abstract

A detailed analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM so the model equilibrates to a desired state. For this manner, four different types of Hebbian learning algorithms have been proposed in the past. Along with the theoretical description of these algorithms, their performance in system modeling problems is investigated in this work. The algorithms are studied in a comparative fashion by using appropriate performance indices and useful conclusions about their training capabilities are experimentally derived.

Original language	English
Title of host publication	IEEE International Conference on Fuzzy Systems
Number of pages	8
Publication date	27 Sept 2011
Pages	851-858
Article number	6007544
ISBN (Print)	9781424473175
DOIs	https://doi.org/10.1109/FUZZY.2011.6007544
Publication status	Published - 27 Sept 2011
Externally published	Yes

Keywords

fuzzy cognitive maps
hebbian learning
system modeling
training

Access to Document

10.1109/FUZZY.2011.6007544

http://www.scopus.com/inward/record.url?scp=80053057168&partnerID=8YFLogxK

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{176dd5333a924ebf80262b04f9893664,

title = "Training Fuzzy Cognitive Maps by using Hebbian learning algorithms: A comparative study",

abstract = "A detailed analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM so the model equilibrates to a desired state. For this manner, four different types of Hebbian learning algorithms have been proposed in the past. Along with the theoretical description of these algorithms, their performance in system modeling problems is investigated in this work. The algorithms are studied in a comparative fashion by using appropriate performance indices and useful conclusions about their training capabilities are experimentally derived.",

keywords = "fuzzy cognitive maps, hebbian learning, system modeling, training",

author = "Papakostas, {G. A.} and Athanasios Polydoros and Koulouriotis, {D. E.} and Tourassis, {V. D.}",

year = "2011",

month = sep,

day = "27",

doi = "10.1109/FUZZY.2011.6007544",

language = "English",

isbn = "9781424473175",

pages = "851--858",

booktitle = "IEEE International Conference on Fuzzy Systems",

}

TY - GEN

T1 - Training Fuzzy Cognitive Maps by using Hebbian learning algorithms

T2 - A comparative study

AU - Papakostas, G. A.

AU - Polydoros, Athanasios

AU - Koulouriotis, D. E.

AU - Tourassis, V. D.

PY - 2011/9/27

Y1 - 2011/9/27

N2 - A detailed analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM so the model equilibrates to a desired state. For this manner, four different types of Hebbian learning algorithms have been proposed in the past. Along with the theoretical description of these algorithms, their performance in system modeling problems is investigated in this work. The algorithms are studied in a comparative fashion by using appropriate performance indices and useful conclusions about their training capabilities are experimentally derived.

AB - A detailed analysis of the Hebbian-like learning algorithms applied to train Fuzzy Cognitive Maps (FCMs) is presented in this paper. These algorithms aim to find appropriate weights between the concepts of the FCM so the model equilibrates to a desired state. For this manner, four different types of Hebbian learning algorithms have been proposed in the past. Along with the theoretical description of these algorithms, their performance in system modeling problems is investigated in this work. The algorithms are studied in a comparative fashion by using appropriate performance indices and useful conclusions about their training capabilities are experimentally derived.

KW - fuzzy cognitive maps

KW - hebbian learning

KW - system modeling

KW - training

U2 - 10.1109/FUZZY.2011.6007544

DO - 10.1109/FUZZY.2011.6007544

M3 - Article in proceeding

AN - SCOPUS:80053057168

SN - 9781424473175

SP - 851

EP - 858

BT - IEEE International Conference on Fuzzy Systems

ER -

Training Fuzzy Cognitive Maps by using Hebbian learning algorithms: A comparative study

Abstract

Keywords

Access to Document

AUB Link

Fingerprint

Cite this