Abstract

A new approach to learning in a multilayer neural network based on a backpropagation algorithm is presented. With a sine-type thresholding function the model is more efficient and able to learn nonnegative interconnections that are suitable for optical implementations.

© 1992 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Generalization of the backpropagation neural network learning algorithm to permit complex weights

Gordon R. Little, Steven C. Gustafson, and Robert A. Senn
Appl. Opt. 29(11) 1591-1592 (1990)

Multilayer optical learning networks

Kelvin Wagner and Demetri Psaltis
Appl. Opt. 26(23) 5061-5076 (1987)

Local learning algorithm for optical neural networks

Yong Qiao and Demetri Psaltis
Appl. Opt. 31(17) 3285-3288 (1992)

References

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
Login to access OSA Member Subscription

Cited By

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
Login to access OSA Member Subscription

Figures (1)

You do not have subscription access to this journal. Figure files 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
Login to access OSA Member Subscription

Tables (1)

You do not have subscription access to this journal. Article tables 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
Login to access OSA Member Subscription

Equations (11)

You do not have subscription access to this journal. Equations 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
Login to access OSA Member Subscription

Metrics

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
Login to access OSA Member Subscription