Transputer based back-propagation neural net emulation system

A transputer based back-propagation neural net emulation system is presented. The authors propose one mapping approach for mesh architecture. The major challenge of this research work is to map the back-propagation neural net model onto transputer arrays for mesh architecture. The OCCAM parallel pro...

Full description

Saved in:
Bibliographic Details
Published in1990 IEEE International Symposium on Circuits and Systems (ISCAS) pp. 1879 - 1882
Main Authors Jou, I.-C., Yung-Chang Tsai
Format Conference Proceeding
LanguageEnglish
Published IEEE 1990
Subjects
Artificial neural networks
Emulation
Natural languages
Neural networks
Neurons
Parallel processing
Parallel programming
Speech recognition
Switches
System testing
Online AccessGet full text

Cover

More Information
Summary:A transputer based back-propagation neural net emulation system is presented. The authors propose one mapping approach for mesh architecture. The major challenge of this research work is to map the back-propagation neural net model onto transputer arrays for mesh architecture. The OCCAM parallel programming language is used for programming the operations of these transputers. Using this transputer based emulation system, a test case for Mandarin (Chinese voice) speech zero to nine recognition is implemented, and encouraging results, i.e. the recognition rate of inside test 99% and outside test 96%, have been obtained.< >
DOI:10.1109/ISCAS.1990.112044