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

URN to cite this document:: urn:nbn:de:bvb:355-epub-268052
DOI to cite this document:: 10.5283/epub.26805

Schmitz, H. J. ; Pöppel, G. ; Wünsch, Friedrich ; Krey, Uwe

Preview

PDF
(2MB)

Date of publication of this fulltext: 23 Nov 2012 14:01

Alternative links to fulltext:DOI

Details

Preview

Export bibliographical data

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 ...