Abstract

A novel type of quantized learning rule with unipolar binary weights that is useful for the optical implementation of neural networks is reported. An input-dependent thresholding operation is also proposed to remove the unwanted effects that are due to the insufficient contrast ratio of spatial light modulators as synaptic connection devices. Moreover, we experimentally demonstrate the recognition of 26 characters of the alphabet by using the single set of an optoelectronic three-layered network.

© 1990 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Optical implementation of large-scale neural networks using a time-division-multiplexing technique

Masaya Oita, Jun Ohta, Shuichi Tai, and Kazuo Kyuma
Opt. Lett. 15(4) 227-229 (1990)

Incoherent dynamic lenslet array processor

D. J. Wiley, I. Glaser, B. K. Jenkins, and A. A. Sawchuk
Appl. Opt. 32(20) 3641-3653 (1993)

Image identification system based on an optical broadcast neural network processor

Marta Ruiz-Llata and Horacio Lamela-Rivera
Appl. Opt. 44(12) 2366-2376 (2005)

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 (4)

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

Equations (4)

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