Title :
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
fDate :
30 Aug-3 Sep 1992
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;
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
DOI :
10.1109/ICPR.1992.201719
