A logical neural network that adapts to changes in the pattern environment

Author

Tambouratzis, G. ; Stonham, T.J.

Author_Institution

Dept. of Electr. Eng., Brunel Univ., Uxbridge, UK

fYear

1992

fDate

30 Aug-3 Sep 1992

Firstpage

46

Lastpage

49

Abstract

An online, unsupervised training algorithm is presented, which allows a logical neural network already trained to identify classes of objects to adapt to changes in the environment. This algorithm enables the system to operate continuously, without danger of overgeneralisation and displays useful noise-reduction properties. Results indicating its capabilities and characteristics in this adaptation task are described. The algorithm´s self-organisation characteristics are also evaluated

Keywords

image recognition; neural nets; self-adjusting systems; unsupervised learning; adaptive algorithm; learning systems; logical neural network; noise-reduction; online unsupervised training algorithm; pattern recognition; self-organisation characteristics; Adaptive algorithm; Biological neural networks; Displays; Hamming distance; Intelligent networks; Logic functions; Neural networks; Random access memory; Unsupervised learning; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on

Conference_Location

The Hague

Print_ISBN

0-8186-2915-0

Type

conf

DOI

10.1109/ICPR.1992.201719

Filename

201719