Auto-associative memory by universal learning networks (ULNs)

K. Shibuta, K. Hirasawa, Jinglu Hu, J. Murata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a new auto correlation associative memory using universal learning networks (ULNs). The main purpose of this paper is to realize associative memory by training the network. Although so many useful models have been devised, there are some problems related to associative memory, such as the limitation of storage capacity or too small attractors of stored memories. To solve these problems, we obtain memory network by training network parameters not by calculating them in the conventional methods. Furthermore, we introduce "don't care nodes" into the networks just to enlarge network size and give more flexibility. We could verify that this method improves the memory capacity by computer simulations.

Original languageEnglish
Title of host publicationICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Subtitle of host publicationComputational Intelligence for the E-Age
EditorsJagath C. Rajapakse, Xin Yao, Lipo Wang, Kunihiko Fukushima, Soo-Young Lee
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages388-392
Number of pages5
ISBN (Electronic)9810475241, 9789810475246
DOIs
Publication statusPublished - 2002
Event9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
Duration: Nov 18 2002Nov 22 2002

Publication series

NameICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
Volume1

Other

Other9th International Conference on Neural Information Processing, ICONIP 2002
Country/TerritorySingapore
CitySingapore
Period11/18/0211/22/02

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Fingerprint

Dive into the research topics of 'Auto-associative memory by universal learning networks (ULNs)'. Together they form a unique fingerprint.

Cite this