Title :
LSSM based Korean character recognition and colored neural nets
Author :
Kim, Sung Tae ; Herath, Susantha
Author_Institution :
Dept. of Electr. & Comput. Eng., Drexel Univ., Philadelphia, PA, USA
Abstract :
The linear systems in a saturated mode (LSSM) model is applied to Korean character recognition. In general, conventional neural networks without uncommitted neurons cannot incorporate new patterns for recognition, and pattern recognition and reconstruction of many learned patterns cannot be performed simultaneously. It is shown that these problems can be solved by using a colored neural net model
Keywords :
character recognition; character sets; learning systems; linear systems; neural nets; Korean character recognition; colored neural nets; learned patterns; linear systems in a saturated mode; uncommitted neurons; Character recognition; Computational modeling; Computer science; Differential equations; Linear systems; Machine intelligence; Neural networks; Neurons; Parallel processing; Pattern recognition;
Conference_Titel :
Intelligent Control, 1990. Proceedings., 5th IEEE International Symposium on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-8186-2108-7
DOI :
10.1109/ISIC.1990.128477
