Share Email Print

Optical Engineering

Study of the approximation capabilities of two four-layered neural networks
Author(s): Claudia Mello-Thoms; Stanley M. Dunn
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

The approximation capabilities of two different four-layered neural networks are studied. First, a network with the backpropagation algorithm is analyzed, and its error surface, convergence properties, and network design are considered. An alternative to the backpropagation approach is presented, namely, we construct a network that uses a one- pass algorithm. We show that the proposed network can correctly classify N different patterns with 4 ?N?3 hidden units. We also show that an arbitrarily small approximation error can be obtained for this network by adjusting the appropriate parameters.

Paper Details

Date Published: 1 March 1998
PDF: 9 pages
Opt. Eng. 37(3) doi: 10.1117/1.601923
Published in: Optical Engineering Volume 37, Issue 3
Show Author Affiliations
Claudia Mello-Thoms, Rutgers Univ. (United States)
Stanley M. Dunn, Rutgers Univ. (United States)

© SPIE. Terms of Use
Back to Top