Self-organizing neural networks by dynamic and spatial changing weights

N. Homma, M. M. Gupta, M. Yoshizawa, K. Abe

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

Abstract

We propose a self-organizing neural structure with dynamic and spatial changing weights for forming a feature space representation of concepts. An essential core of this self-organization is an appropriate combination of an unsupervised learning with incomplete information for the dynamic changing and an extended Hebbian rule for a signal-driven spatial changing. A concept formation problem requires the neural network to acquire the complete feature space structure of concept information using an incomplete observation of the concept. The informational structure can be stored as the connection structure of self-organizing network by using the two rules: the Hebbian rule can create a necessary connection, while unsupervised learning can delete unnecessary connections. Finally concept formation ability of the proposed neural network is proven under some conditions.

Original languageEnglish
Title of host publication4th International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003
EditorsNii O. Attoh-Okine, Bilal M. Ayyub
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages129-134
Number of pages6
ISBN (Electronic)0769519970, 9780769519975
DOIs
Publication statusPublished - 2003
Event4th International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003 - College Park, United States
Duration: 2003 Sep 212003 Sep 24

Publication series

Name4th International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003

Other

Other4th International Symposium on Uncertainty Modeling and Analysis, ISUMA 2003
CountryUnited States
CityCollege Park
Period03/9/2103/9/24

Keywords

  • Backpropagation algorithms
  • Biological neural networks
  • Biomedical engineering
  • Cognition
  • Educational institutions
  • Hebbian theory
  • Learning systems
  • Neural networks
  • Self-organizing networks
  • Unsupervised learning

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Control and Optimization
  • Modelling and Simulation

Fingerprint Dive into the research topics of 'Self-organizing neural networks by dynamic and spatial changing weights'. Together they form a unique fingerprint.

Cite this