Go to content
UR Home

Fast recognition of real objects by an optimized hetero-associative neural network

Schmitz, H. J., Pöppel, G., Wünsch, Friedrich and Krey, Uwe (1990) Fast recognition of real objects by an optimized hetero-associative neural network. Journal de Physique 51 (2), pp. 167-183.

[img]
Preview
PDF
Download (2MB)
Date of publication of this fulltext: 23 Nov 2012 14:01

at publisher (via DOI)


Abstract

We have developed and realized a concept which is very well suited for a quick recognition of highly correlated patterns. For a hetero-associative memory we used a minimal optimized output code (index memory). We constructed a tree structure in which the assignment of indices has been optimized by simulated annealing. Thus the algorithm for optimal stability of the learned patterns works most ...

plus


Export bibliographical data



Item type:Article
Date:January 1990
Institutions:Physics > Others > Dr. Friedrich Wünsch
Identification Number:
ValueType
10.1051/jphys:01990005102016700DOI
Classification:
NotationType
0705MPACS
Keywords:computerised pattern recognition -- learning systems -- neural nets -- optical character recognition -- optimisation -- parallel processing
Dewey Decimal Classification:500 Science > 530 Physics
Status:Published
Refereed:Unknown
Created at the University of Regensburg:Unknown
Item ID:26805
Owner only: item control page

Downloads

Downloads per month over past year

  1. Homepage UR

University Library

Publication Server

Contact:

Publishing: oa@ur.de

Dissertations: dissertationen@ur.de

Research data: daten@ur.de

Contact persons