A coded block neural network system suitable for VLSI implementation using an adaptive learning-rate epoch-based back propagation technique
Resource
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Journal
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Pages
-
Date Issued
1993-05
Date
1993-05
Author(s)
Mao, M.W.
Chen, B.Y.
Kuo, J.B.
DOI
N/A
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.>
Type
journal article
File(s)![Thumbnail Image]()
Loading...
Name
00394137.pdf
Size
294.85 KB
Format
Adobe PDF
Checksum
(MD5):ae5f1a70cf9ce322999241bc8f1d78c6