9 March 1999 Feedback neural network for pattern recognition
Author Affiliations +
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.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ismail Salih, Stanley H. Smith, "Feedback neural network for pattern recognition", Proc. SPIE 3647, Applications of Artificial Neural Networks in Image Processing IV, (9 March 1999); doi: 10.1117/12.341120; https://doi.org/10.1117/12.341120
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Texture-based steganalysis: results for color images
Proceedings of SPIE (October 18 2004)
Error Correcting Optical Syntactic Pattern Recognizers
Proceedings of SPIE (August 11 1987)
Algorithms for adaptive nonlinear pattern recognition
Proceedings of SPIE (September 29 2011)
Symmetry recognition in images
Proceedings of SPIE (July 19 1999)
Image algebra networks for pattern classification
Proceedings of SPIE (June 30 1994)

Back to Top