DocumentCode :
3257516
Title :
Steps towards a VLSI implementation of the back propagation algorithm: non-linear synaptic functions
Author :
Bisset, D.L. ; Daniell, P.M.
Author_Institution :
Electron. Eng. Lab., Kent Univ., Canterbury, UK
fYear :
1989
fDate :
0-0 1989
Abstract :
Summary form only given. A theoretical modification to the back error propagation (BEP) equations is presented which allows more efficient hardware implementation to be made when fabricating in analog VLSI. Through simulation results it is shown how this modification affects the performance of the BEP algorithm when performing simple learning tasks.<>
Keywords :
VLSI; learning systems; neural nets; VLSI implementation; analog VLSI; back error propagation equations; back propagation algorithm; efficient hardware implementation; nonlinear synaptic functions; performance; simple learning tasks; simulation results; theoretical modification; Learning systems; Neural networks; Very-large-scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
Type :
conf
DOI :
10.1109/IJCNN.1989.118450
Filename :
118450
Link To Document :
بازگشت