Discrete all-positive multilayer perceptrons for optical implementation

Perry D. Moerland; Emile Fiesler; Indu F. Saxena

doi:10.1117/1.601963

1 April 1998 Discrete all-positive multilayer perceptrons for optical implementation

Perry D. Moerland, Emile Fiesler, Indu F. Saxena

Optical Engineering, Vol. 37, Issue 4, (April 1998). https://doi.org/10.1117/1.601963

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.

Citation Download Citation

Perry D. Moerland, Emile Fiesler, and Indu F. Saxena "Discrete all-positive multilayer perceptrons for optical implementation," Optical Engineering 37(4), (1 April 1998). https://doi.org/10.1117/1.601963

Published: 1 April 1998

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available