Title :
A radical-partitioned neural network system using a modified sigmoid function and a weight-dotted radical selector for large-volume Chinese character recognition VLSI
Author :
Kuo, J.B. ; Chen, B.Y. ; Mao, M.W.
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Inst. of Technol., Taipei, Taiwan
fDate :
30 May-2 Jun 1994
Abstract :
This paper presents a radical-partitioned neural network system using a modified sigmoid function and a weight-dotted radical selector for large-volume Chinese characters recognition VLSI. With a modified sigmoid function and the weight-dotted radical selector, the recognition rate of 1000 radical-partitioned Chinese characters can be enhanced to 90% from 70% for the input samples with 15% random errors as compared to the system without it
Keywords :
VLSI; backpropagation; block codes; character recognition; neural nets; Chinese character recognition; VLSI; large-volume Chinese characters; modified sigmoid function; radical-partitioned neural network system; random errors; recognition rate; weight-dotted radical selector; Adaptive systems; Character recognition; Convergence; Multiplexing; Neural networks; Very large scale integration;
Conference_Titel :
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location :
London
Print_ISBN :
0-7803-1915-X
DOI :
10.1109/ISCAS.1994.409593
