Title :
Novel learning method for analogue neural networks
Author :
Matsumoto, Tad ; Koga, Masafumi
Author_Institution :
NTT Transmission Syst. Labs., Kanagawa, Japan
fDate :
7/19/1990 12:00:00 AM
Abstract :
An analogue-neural-network learning method based on hardware is proposed. All the network parameters are oscillated with slightly different frequencies, and the spectra appearing in the error signal are used to change the parameters. Learning can be carried out without knowing the internal conditions of neural networks.
Keywords :
learning systems; neural nets; analogue neural networks; analogue-neural-network learning method; different frequencies; error signal; multifrequency oscillation learning method; network parameters oscillated; parameter changing; spectra appearing;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19900735
