Influence of interconnection weight discretization and noise in an optoelectronic neural network
Optics Letters, Vol. 14, Issue 17, pp. 928-930 (1989)
http://dx.doi.org/10.1364/OL.14.000928
Acrobat PDF (452 KB)
Abstract
The effect of discretizing interconnection weight strengths in an optoelectronic learning neural network based on the backpropagation algorithm is investigated. We discuss how discretization arises in such an implementation. Using computer simulations we find that learning performance, as tested on the two-input XOR problem, is poor but that the addition of noise to the system results in substantial improvement.
© 1989 Optical Society of America
Citation
A. Von Lehmen, E. G. Paek, P. F. Liao, A. Marrakchi, and J. S. Patel, "Influence of interconnection weight discretization and noise in an optoelectronic neural network," Opt. Lett. 14, 928-930 (1989)
http://www.opticsinfobase.org/ol/abstract.cfm?URI=ol-14-17-928
You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
You do not have subscription access to this journal. Article level metrics are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Log in to access OSA Member Subscription
« Previous Article | Next Article »
OSA is a member of 