2010 | OriginalPaper | Buchkapitel
Classifying Patterns Using Fuzzy Cognitive Maps
verfasst von : G. A. Papakostas, D. E. Koulouriotis
Erschienen in: Fuzzy Cognitive Maps
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This chapter is focused on the use of Fuzzy Cognitive Maps (FCMs) in classifying patterns, as alternative to the traditional classifiers such as neural networks or even as collaborators, in achieving better classification capabilities. By defining the classification procedure as the equilibrium point achieved by applying common inference laws, a FCM can simulate a typical classifier that maps a set of inputs to specific output values.
The classification capabilities of the FCM classifiers are studied in several pattern classification problems, while the ability of the FCM to store knowledge about the problem in hand is investigated in conjunction to the nodes’ type of activation function and the inference law used. Appropriate experiments are taken place, in order to analyze the behavior of the FCM-based classifiers, in well known benchmark problems.