Feature Enhanced optical Interpattern Associative neural network

Shutian Liu; Wenlu Wang; Ruibo Wang; Jie Wu; Chunfei Li

doi:10.1117/12.983194

Feature Enhanced optical Interpattern Associative neural network

Shutian Liu
, Wenlu Wang
, Ruibo Wang
, Jie Wu
, Chunfei Li

School of Physics

Harbin Institute of Technology

Research output: Contribution to journal › Conference article › peer-review

Abstract

In this paper we propose a Feature Enhanced Interpattern Associative (FEIPA) optical neural network. The common part of the stored patterns is regarded as redundance and its contribution in the association process is discarded. Therefore, the output before thresholding is more uniform, and it is more easier for the thresholding performance and increase the iteration speed. Furthermore, the optical implementation is much easier because all the elements of the interconnection matrix are non-negative and unipolar. The theoretical description and the experimental results are presented.

Original language	English
Pages (from-to)	105-110
Number of pages	6
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1773
DOIs	https://doi.org/10.1117/12.983194
State	Published - 2 Feb 1993
Event	Photonics for Computers, Neural Networks, and Memories 1992 - San Diego, United States Duration: 22 Jul 1992 → …

Access to Document

10.1117/12.983194

Cite this

@article{baee5b274b4649c7a015c4bb7605d1d5,

title = "Feature Enhanced optical Interpattern Associative neural network",

abstract = "In this paper we propose a Feature Enhanced Interpattern Associative (FEIPA) optical neural network. The common part of the stored patterns is regarded as redundance and its contribution in the association process is discarded. Therefore, the output before thresholding is more uniform, and it is more easier for the thresholding performance and increase the iteration speed. Furthermore, the optical implementation is much easier because all the elements of the interconnection matrix are non-negative and unipolar. The theoretical description and the experimental results are presented.",

author = "Shutian Liu and Wenlu Wang and Ruibo Wang and Jie Wu and Chunfei Li",

year = "1993",

month = feb,

day = "2",

doi = "10.1117/12.983194",

language = "英语",

volume = "1773",

pages = "105--110",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Feature Enhanced optical Interpattern Associative neural network

AU - Liu, Shutian

AU - Wang, Wenlu

AU - Wang, Ruibo

AU - Wu, Jie

AU - Li, Chunfei

PY - 1993/2/2

Y1 - 1993/2/2

N2 - In this paper we propose a Feature Enhanced Interpattern Associative (FEIPA) optical neural network. The common part of the stored patterns is regarded as redundance and its contribution in the association process is discarded. Therefore, the output before thresholding is more uniform, and it is more easier for the thresholding performance and increase the iteration speed. Furthermore, the optical implementation is much easier because all the elements of the interconnection matrix are non-negative and unipolar. The theoretical description and the experimental results are presented.

AB - In this paper we propose a Feature Enhanced Interpattern Associative (FEIPA) optical neural network. The common part of the stored patterns is regarded as redundance and its contribution in the association process is discarded. Therefore, the output before thresholding is more uniform, and it is more easier for the thresholding performance and increase the iteration speed. Furthermore, the optical implementation is much easier because all the elements of the interconnection matrix are non-negative and unipolar. The theoretical description and the experimental results are presented.

UR - https://www.scopus.com/pages/publications/85075923285

U2 - 10.1117/12.983194

DO - 10.1117/12.983194

M3 - 会议文章

AN - SCOPUS:85075923285

SN - 0277-786X

VL - 1773

SP - 105

EP - 110

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

T2 - Photonics for Computers, Neural Networks, and Memories 1992

Y2 - 22 July 1992

ER -

Feature Enhanced optical Interpattern Associative neural network

Abstract

Access to Document

Other files and links

Fingerprint

Cite this