Improved Kohonen Feature Map Associative Memory with Refractoriness based on Area Representation

Author

Uda, Yoichi ; Osana, Yuko

Author_Institution

Sch. of Comput. Sci., Tokyo Univ. of Technol., Tokyo

fYear

2008

fDate

12-15 Oct. 2008

Firstpage

2127

Lastpage

2132

Abstract

In this paper, we propose an Improved Kohonen Feature Map Associative Memory with Refractoriness based on Area Representation. This model is based on the Kohonen Feature Map Associative Memory with Refractoriness based on Area Representation. The proposed model can realize one-to-many associations of binary/analog patterns. This model has enough robustness for damaged neurons when analog patterns are memorized. Moreover, the learning speed of the proposed model is faster than that of the conventional model. We carried out a series of computer experiments and confirmed the effectiveness of the proposed model.

Keywords

learning (artificial intelligence); self-organising feature maps; Kohonen feature map associative memory; area representation; self-organizing maps; successive learning; Associative memory; Biological neural networks; Computer science; Hopfield neural networks; Information processing; Neural networks; Neurons; Resonance; Robustness; Subspace constraints; Area Representation; Kohonen Feature Map (Self-Organizing Map); Refractriness; Successive Learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2008. SMC 2008. IEEE International Conference on

Conference_Location

Singapore

ISSN

1062-922X

Print_ISBN

978-1-4244-2383-5

Electronic_ISBN

1062-922X

Type

conf

DOI

10.1109/ICSMC.2008.4811606

Filename

4811606