DocumentCode :
2612637
Title :
Applying logic neural networks to hand-written character recognition tasks
Author :
Tambouratzis, G.
Author_Institution :
Inst. for Language & Speen Processing, Athens, Greece
fYear :
1996
fDate :
16-19 Nov. 1996
Firstpage :
268
Lastpage :
271
Abstract :
This article discusses the implementation of a hand-written character recognition task using neural networks. Two logic neural networks-the WISARD (I. Aleksander and H. Morton, 1990) and the SOLNN (G. Tambouratzis and T.J. Stonham, 1993)-are compared on the basis of their classification accuracy. The results obtained are compared to these of other researchers, to objectively assess the success of the neural networks in classifying the dataset.
Keywords :
character recognition; handwriting recognition; neural nets; pattern classification; self-organising feature maps; SOLNN; WISARD; classification accuracy; handwritten character recognition; logic neural networks; n-tuple statistical pattern recognition; self-organising logic neural network; Character recognition; Hamming distance; Logic circuits; Natural languages; Neural networks; Pattern recognition; Random access memory; Read-write memory; Retina; Speech processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Tools with Artificial Intelligence, 1996., Proceedings Eighth IEEE International Conference on
ISSN :
1082-3409
Print_ISBN :
0-8186-7686-7
Type :
conf
DOI :
10.1109/TAI.1996.560461
Filename :
560461
Link To Document :
بازگشت