DocumentCode :
2611850
Title :
A coded block neural network system suitable for VLSI implementation using an adaptive learning-rate epoch-based back propagation technique
Author :
Mao, M.W. ; Chen, B.Y. ; Kuo, J.B.
Author_Institution :
Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
fYear :
1993
fDate :
3-6 May 1993
Firstpage :
1967
Abstract :
A coded block adaptive neural network system is presented. It is suitable for VLSI implementation using an adaptive learning-rate epoch-based backpropagation technique to train large-volume input patterns. Using this coded block neural network system, 500 frequently-used Chinese characters were successfully trained in 47.2 hours using a 28 MIPs computer. Training of the epoch-based system is much less sensitive to initial weights and irrelevant to the order of the input patterns as compared to the system using the conventional backpropagation algorithm
Keywords :
VLSI; backpropagation; block codes; character recognition; 28 MIPS; 47.2 hrs; Chinese characters; VLSI implementation; adaptive learning-rate technique; coded block neural network system; epoch-based back propagation technique; initial weights; input patterns; large-volume input patterns; Adaptive systems; Computer hacking; Computer networks; Lattices; Neural networks; Neurons; Pattern recognition; Retina; Tin; Very large scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-1281-3
Type :
conf
DOI :
10.1109/ISCAS.1993.394137
Filename :
394137
Link To Document :
بازگشت