Separation of superimposed pattern and many-to-many associations by chaotic neural networks

Yuko Osana, Masafumi Hagiwara

Research output: Contribution to conferencePaper

30 Citations (Scopus)

Abstract

In this paper, we propose a Chaotic Associative Memory (CAM). It has two distinctive features: (1) it can recall correct stored patterns from superimposed input; (2) it can deal with many-to-many associations. As for the first feature, when a stored pattern is given to the conventional chaotic neural network as an external input continuously, around the input pattern is searched. The proposed model makes use of the above property in order to separate superimposed patterns. As for the second one, most of the conventional associative memories can not deal with many-to-many associations because the superimposed pattern caused by the stored common data. However, since the proposed model can separate the superimposed pattern, it can deal with many-to-many associations. A series of computer simulations shows the effectiveness of the proposed model.

Original languageEnglish
Pages514-519
Number of pages6
Publication statusPublished - 1998 Jan 1
EventProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) - Anchorage, AK, USA
Duration: 1998 May 41998 May 9

Other

OtherProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)
CityAnchorage, AK, USA
Period98/5/498/5/9

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Separation of superimposed pattern and many-to-many associations by chaotic neural networks'. Together they form a unique fingerprint.

  • Cite this

    Osana, Y., & Hagiwara, M. (1998). Separation of superimposed pattern and many-to-many associations by chaotic neural networks. 514-519. Paper presented at Proceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3), Anchorage, AK, USA, .