Share Email Print

Proceedings Paper

Feedback neural network for pattern recognition
Author(s): Ismail Salih; Stanley H. Smith
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In the present paper, a new synthesis approach is developed for associate memories based on a modified relaxation algorithm. The design problem, of feedback neural networks for associative memories is formulated as a set of linear inequalities such that the use of pseudo relaxation method is evident. The pseudo relaxation training in the synthesis algorithms is guaranteed to converge for the design of neural networks without any constraints on the connection matrix. To demonstrate the applicability of the present result and to compare the present synthesis approach with existing design methods, a pattern recognition example is considered.

Paper Details

Date Published: 9 March 1999
PDF: 8 pages
Proc. SPIE 3647, Applications of Artificial Neural Networks in Image Processing IV, (9 March 1999); doi: 10.1117/12.341120
Show Author Affiliations
Ismail Salih, Stevens Institute of Technology (United States)
Stanley H. Smith, Stevens Institute of Technology (United States)

Published in SPIE Proceedings Vol. 3647:
Applications of Artificial Neural Networks in Image Processing IV
Nasser M. Nasrabadi; Aggelos K. Katsaggelos, Editor(s)

© SPIE. Terms of Use
Back to Top