Articles

Discrete all-positive multilayer perceptrons for optical implementation

[+] Author Affiliations
Perry D. Moerland

Institut Dalle Molle d’Intelligence Artificielle Perceptive, Case Postal 592, CH-1920?Martigny, Switzerland perry@idiap.ch

Emile Fiesler, Indu Saxena

Physical Optics Corporation, Gramercy Place, Torrance, California?90501

Opt. Eng. 37(4), 1305-1315 (Apr 01, 1998). doi:10.1117/1.601963
History: Received Feb. 14, 1997; Revised Nov. 8, 1997; Accepted Nov. 10, 1997
Text Size: A A A

Abstract

All-optical multilayer perceptrons differ in various ways from the ideal neural network model. Examples are the use of nonideal activation functions, which are truncated, asymmetric, and have a nonstandard gain; restriction of the network parameters to non-negative values, and the limited accuracy of the weights. A backpropagation-based learning rule is presented that compensates for these nonidealities and enables the implementation of all-optical multilayer perceptrons where learning occurs under computer control. The good performance of this learning rule, even when using a small number of weight levels, is illustrated by a series of computer simulations incorporating the nonidealities. © 1998 Society of Photo-Optical Instrumentation Engineers.

© 1998 Society of Photo-Optical Instrumentation Engineers

Topics

Multilayers

Citation

Perry D. Moerland ; Emile Fiesler and Indu Saxena
"Discrete all-positive multilayer perceptrons for optical implementation", Opt. Eng. 37(4), 1305-1315 (Apr 01, 1998). ; http://dx.doi.org/10.1117/1.601963


Figures

Tables

References

Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement

 

 

 

  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.