Title :
Evolutionary learning to optimise mapping in n-Tuple networks
Author :
Bishop, J.M. ; Crowe, A.A. ; Michinton, P.R. ; Mitchell, R.J.
Author_Institution :
Dept. of Cybern., Reading Univ., UK
Abstract :
The use of n-Tuple networks as pattern recognition devices is well known. Networks are able to recognise and discriminate between different classes of data if each class is taught into a separate discriminator. If the different classes are too similar, however, the system can have difficulty discriminating between the classes. This paper describes a novel method of optimising the learning strategy to minimise this problem
Keywords :
computerised pattern recognition; learning systems; optimisation; discriminator; learning strategy; mapping optimisation; n-Tuple networks; pattern recognition; simulated annealing;
Conference_Titel :
Machine Learning, IEE Colloquium on
Conference_Location :
London