Share Email Print

Proceedings Paper

Class of learning algorithms for multilayer perceptron
Author(s): M. Abbasi; Mohammed R. Sayeh
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A class of learning techniques for neural networks can be considered as optimization problems. The connection strengths are modified such that the difference between the network response and a desired response Is minimized. In this paper the learning techniques based on the gradient momentum Newton and quasi-Newton methods are considered. A learning algorithm is also developed based on the conjugate gradient technique. These learning techniques are applied to the Exclusive-OR problem for comparison of their performance. For this problem the algorithm based on the conjugate gradient technique converges faster than the other algorithms. 2.

Paper Details

Date Published: 1 March 1991
PDF: 6 pages
Proc. SPIE 1396, Applications of Optical Engineering: Proceedings of OE/Midwest '90, (1 March 1991); doi: 10.1117/12.47758
Show Author Affiliations
M. Abbasi, Southern Illinois Univ./Carbondale (United States)
Mohammed R. Sayeh, Southern Illinois Univ./Carbondale (United States)

Published in SPIE Proceedings Vol. 1396:
Applications of Optical Engineering: Proceedings of OE/Midwest '90
Rudolph P. Guzik; Hans E. Eppinger; Richard E. Gillespie; Mary Kathryn Dubiel; James E. Pearson, Editor(s)

© SPIE. Terms of Use
Back to Top