Feature-enhanced optical interpattern-associative neural network model and its optical implementation

Chunfei Li; Wenlu Wang; Shutian Liu; Jie Wu

Feature-enhanced optical interpattern-associative neural network model and its optical implementation

Chunfei Li^*
, Wenlu Wang
, Shutian Liu
, Jie Wu

^*Corresponding author for this work

School of Physics

Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › 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 hence, it is easier for the thresholding performance and increases 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
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Publisher	Publ by Int Soc for Optical Engineering
Pages	161-167
Number of pages	7
ISBN (Print)	0819410128
State	Published - 1993
Event	Optical Computing and Neural Networks - Hsinchu, Taiwan Duration: 16 Dec 1992 → 17 Dec 1992

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1812
ISSN (Print)	0277-786X

Conference

Conference	Optical Computing and Neural Networks
City	Hsinchu, Taiwan
Period	16/12/92 → 17/12/92

Cite this

@inproceedings{18af2b283e1b4edf95233edfe2abdb69,

title = "Feature-enhanced optical interpattern-associative neural network model and its optical implementation",

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 hence, it is easier for the thresholding performance and increases 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 = "Chunfei Li and Wenlu Wang and Shutian Liu and Jie Wu",

year = "1993",

language = "英语",

isbn = "0819410128",

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

publisher = "Publ by Int Soc for Optical Engineering",

pages = "161--167",

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

note = "Optical Computing and Neural Networks ; Conference date: 16-12-1992 Through 17-12-1992",

}

Li, C, Wang, W, Liu, S & Wu, J 1993, Feature-enhanced optical interpattern-associative neural network model and its optical implementation. in Proceedings of SPIE - The International Society for Optical Engineering. Proceedings of SPIE - The International Society for Optical Engineering, vol. 1812, Publ by Int Soc for Optical Engineering, pp. 161-167, Optical Computing and Neural Networks, Hsinchu, Taiwan, 16/12/92.

Feature-enhanced optical interpattern-associative neural network model and its optical implementation. / Li, Chunfei; Wang, Wenlu; Liu, Shutian et al.
Proceedings of SPIE - The International Society for Optical Engineering. Publ by Int Soc for Optical Engineering, 1993. p. 161-167 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 1812).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Feature-enhanced optical interpattern-associative neural network model and its optical implementation

AU - Li, Chunfei

AU - Wang, Wenlu

AU - Liu, Shutian

AU - Wu, Jie

PY - 1993

Y1 - 1993

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 hence, it is easier for the thresholding performance and increases 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 hence, it is easier for the thresholding performance and increases 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/0027147262

M3 - 会议稿件

AN - SCOPUS:0027147262

SN - 0819410128

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 161

EP - 167

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

PB - Publ by Int Soc for Optical Engineering

T2 - Optical Computing and Neural Networks

Y2 - 16 December 1992 through 17 December 1992

ER -

Feature-enhanced optical interpattern-associative neural network model and its optical implementation

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this