DocumentCode
510068
Title
Multiperceptron Architecture Based on the Potts Model for Pattern Identification
Author
Kryzhanovsky, Vladimir
Author_Institution
Center of Opt.-Neural Technol., Russian Acad. of Sci., Moscow, Russia
Volume
2
fYear
2009
fDate
7-8 Nov. 2009
Firstpage
554
Lastpage
558
Abstract
A multiperceptron architecture based on the Potts model is presented. It is shown that the storage capacity of this architecture grows linearly with the increase of the number of perceptrons. The combination of perceptrons is useful when one perceptron is unable to solve an identification task. The method can be applied for q-ary or binary patterns.
Keywords
Potts model; multilayer perceptrons; Potts model; multiperceptron architecture; pattern identification; Artificial intelligence; Associative memory; Character recognition; Computational intelligence; Computer architecture; Neural networks; Neurons; Pattern analysis; Region 8; Signal mapping; Perceptron; Potts model; pattern recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on
Conference_Location
Shanghai
Print_ISBN
978-1-4244-3835-8
Electronic_ISBN
978-0-7695-3816-7
Type
conf
DOI
10.1109/AICI.2009.472
Filename
5375920
Link To Document