Share Email Print

Proceedings Paper

Feature-enhanced IPA neural network and optical realization
Author(s): Wenlu Wang; Minxian Wu; Shutian Liu; Jie Wu; Chunfei Li
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The dynamic behavior of a neural network is demonstrated by its interconnection weighted matrix. In this paper, we present a Feature Enhanced Interpattern Association (FEIPA) neural network model which is sensitive to special features of reference patterns in the reconstruction. We think of the common part of the stored patterns as redundance and discard its contributions in the associating process. It is equal to enhance the role of special features of the reference pattern in the IWM and in the reconstruction procession. Therefore the IWM of FEIPA is well-distributed and the output before threshold is a little more uniform than that of IPA model. A 2D (8 X 8) optical system is constructed using lenslet array as interconnection to realize the FEIPA model. Digital simulation and experiment results are provided.

Paper Details

Date Published: 9 November 1993
PDF: 8 pages
Proc. SPIE 2026, Photonics for Processors, Neural Networks, and Memories, (9 November 1993); doi: 10.1117/12.163593
Show Author Affiliations
Wenlu Wang, Tsinghua Univ. (China)
Minxian Wu, Tsinghua Univ. (China)
Shutian Liu, Harbin Institute of Technology (China)
Jie Wu, Harbin Institute of Technology (China)
Chunfei Li, Harbin Institute of Technology (China)

Published in SPIE Proceedings Vol. 2026:
Photonics for Processors, Neural Networks, and Memories
Stephen T. Kowel; William J. Miceli; Joseph L. Horner; Bahram Javidi; Stephen T. Kowel; William J. Miceli, Editor(s)

© SPIE. Terms of Use
Back to Top