DocumentCode
2836616
Title
Transputer based Hopfield neural net emulation system for pattern recognition
Author
Jou, I-Chang ; Tsai, Yung-Chang
Author_Institution
Telecommun. Lab., Minist. of Commun., Chung-Li, Taiwan
fYear
1989
fDate
22-24 Nov 1989
Firstpage
367
Lastpage
372
Abstract
A transputer-base Hopfield neural net emulation system for pattern recognition is presented. The Hopfield neural net is constructed by the transputers in mesh architectures. The cross-points of the mesh represent the basic processing element of the neural net. The concurrent OCCAM language is used for software programming and data transfer control. Using this system, certain specific pattern recognition is realized. It is shown that the performance of pattern recognition with a Hopfield neural net is encouraging and acceptable
Keywords
computerised pattern recognition; neural nets; parallel processing; transputers; virtual machines; concurrent OCCAM language; data transfer control; mesh architectures; pattern recognition; software programming; transputer-base Hopfield neural net emulation system; Computer architecture; Emulation; Hopfield neural networks; Microcomputers; Microprocessors; Neural networks; Parallel processing; Pattern recognition; Switches; Throughput;
fLanguage
English
Publisher
ieee
Conference_Titel
TENCON '89. Fourth IEEE Region 10 International Conference
Conference_Location
Bombay
Type
conf
DOI
10.1109/TENCON.1989.176961
Filename
176961
Link To Document