OPTOELECTRONIC THRESHOLDING MODULE FOR WINNER-TAKE-ALL OPERATIONS IN OPTICAL NEURAL NETWORKS

被引：13

作者：

BERGERON, A ^{[1
]}

ARSENAULT, HH ^{[1
]}

EUSTACHE, E ^{[1
]}

GINGRAS, D ^{[1
]}

机构：

[1] UNIV LAVAL, CTR OPT PHOTON & LASER, ST FOY G1K 7P4, PQ, CANADA

来源：

APPLIED OPTICS | 1994年 / 33卷 / 08期

关键词：

OPTICAL NEURAL NETWORKS; LIQUID-CRYSTAL TELEVISION; OPTOELECTRONIC THRESHOLDER; WINNER TAKE ALL; CORRELATION;

D O I：

10.1364/AO.33.001463

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

A simple optoelectronic architecture for carrying out optical thresholding operations is proposed. The architecture is suitable for optical neural network implementations and for image processing. The module is based on liquid-crystal television, on a CCD camera, and on beam-sampling optical components. The module does not need an additional light source, shows translation invariance, and does not break the beam propagation path. Experimental results involving images and correlations are presented. Finally, an architecture for an automatic winner-take-all extractor for neural network architectures is proposed.

引用

页码：1463 / 1468

页数：6

共 50 条

[1] WINNER-TAKE-ALL CELLULAR NEURAL NETWORKS
SEILER, G
NOSSEK, JA
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 1993, 40 (03): : 184 - 190
[2] Winner-take-all discrete recurrent neural networks
Yi, Z
Heng, PA
Fung, PF
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 2000, 47 (12): : 1584 - 1589
[3] OPTOELECTRONIC WINNER-TAKE-ALL VLSI SHUNTING NEURAL-NETWORK
KANE, JS
KINCAID, TG
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1995, 6 (05): : 1275 - 1279
[4] Winner-take-all neural networks using the highest threshold
Yang, JF
Chen, CM
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (01): : 194 - 199
[5] Improving the robustness of winner-take-all cellular neural networks
Andrew, LLH
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-ANALOG AND DIGITAL SIGNAL PROCESSING, 1996, 43 (04): : 329 - 334
[6] Training winner-take-all simultaneous recurrent neural networks
Cai, Xindi
Prokhorov, Danil V.
Wunsch, Donald C., II
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2007, 18 (03): : 674 - 684
[7] High Precision Winner-Take-All Circuit for Neural Networks
Paudel, Bijay Raj
Wang, Haibo
Tragoudas, Spyros
Rijal, Omkar
2023 IEEE 36TH INTERNATIONAL SYSTEM-ON-CHIP CONFERENCE, SOCC, 2023, : 36 - 41
[8] A fast winner-take-all neural networks with the dynamic ratio
Chen, CM
Hsu, MH
Wang, TY
JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 2002, 18 (02) : 211 - 222
[9] WINNER-TAKE-ALL NEURAL NET WITH MEMORY
PANKOVE, J
RADEHAUS, C
WAGNER, K
ELECTRONICS LETTERS, 1990, 26 (06) : 349 - 350
[10] Dynamics of a winner-take-all neural network
Fang, YG
Cohen, MA
Kincaid, TG
NEURAL NETWORKS, 1996, 9 (07) : 1141 - 1154

← 1 2 3 4 5 →