Optically realized feedforward-only Cellular Neural Networks

Krzysztof Slot, T. Roska, Leon O. Chua

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

The Cellular Neutral Network (CNN) paradigm is a framework of locally connected analog, nonlinear, dynamic processing elements. CNNs are useful in many application areas including image processing, robot control, biological modelling, etc. An optical implementation of the CNN model using 'liquid crystal light valves' (LCLV) has some definite advantages (especially higher speed and higher resolution) over a VLSI implementation. However the exceptional computing speed (the speed of light) can be fully exploited when 'feedforward-only' templates alone are used. In this work we show how the processing capabilities of optically-realized feedforward-only CNNs can be increased by combining several serial or parallel operations into a single feedforward template. We also derive conditions on a feedforward template whereby the processing resolution in an optical implementation can be increased.

Original languageEnglish
Pages (from-to)158-166
Number of pages9
JournalAEU. Archiv fur Elektronik und Ubertragungstechnik
Volume46
Issue number3
Publication statusPublished - May 1992

Fingerprint

Cellular neural networks
Processing
Light velocity
Liquid crystals
Image processing
Robots

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Optically realized feedforward-only Cellular Neural Networks. / Slot, Krzysztof; Roska, T.; Chua, Leon O.

In: AEU. Archiv fur Elektronik und Ubertragungstechnik, Vol. 46, No. 3, 05.1992, p. 158-166.

Research output: Contribution to journalArticle

@article{dde860fa02324e42b24a1f74afa5a772,
title = "Optically realized feedforward-only Cellular Neural Networks",
abstract = "The Cellular Neutral Network (CNN) paradigm is a framework of locally connected analog, nonlinear, dynamic processing elements. CNNs are useful in many application areas including image processing, robot control, biological modelling, etc. An optical implementation of the CNN model using 'liquid crystal light valves' (LCLV) has some definite advantages (especially higher speed and higher resolution) over a VLSI implementation. However the exceptional computing speed (the speed of light) can be fully exploited when 'feedforward-only' templates alone are used. In this work we show how the processing capabilities of optically-realized feedforward-only CNNs can be increased by combining several serial or parallel operations into a single feedforward template. We also derive conditions on a feedforward template whereby the processing resolution in an optical implementation can be increased.",
author = "Krzysztof Slot and T. Roska and Chua, {Leon O.}",
year = "1992",
month = "5",
language = "English",
volume = "46",
pages = "158--166",
journal = "AEU - International Journal of Electronics and Communications",
issn = "1434-8411",
publisher = "Urban und Fischer Verlag Jena",
number = "3",

}

TY - JOUR

T1 - Optically realized feedforward-only Cellular Neural Networks

AU - Slot, Krzysztof

AU - Roska, T.

AU - Chua, Leon O.

PY - 1992/5

Y1 - 1992/5

N2 - The Cellular Neutral Network (CNN) paradigm is a framework of locally connected analog, nonlinear, dynamic processing elements. CNNs are useful in many application areas including image processing, robot control, biological modelling, etc. An optical implementation of the CNN model using 'liquid crystal light valves' (LCLV) has some definite advantages (especially higher speed and higher resolution) over a VLSI implementation. However the exceptional computing speed (the speed of light) can be fully exploited when 'feedforward-only' templates alone are used. In this work we show how the processing capabilities of optically-realized feedforward-only CNNs can be increased by combining several serial or parallel operations into a single feedforward template. We also derive conditions on a feedforward template whereby the processing resolution in an optical implementation can be increased.

AB - The Cellular Neutral Network (CNN) paradigm is a framework of locally connected analog, nonlinear, dynamic processing elements. CNNs are useful in many application areas including image processing, robot control, biological modelling, etc. An optical implementation of the CNN model using 'liquid crystal light valves' (LCLV) has some definite advantages (especially higher speed and higher resolution) over a VLSI implementation. However the exceptional computing speed (the speed of light) can be fully exploited when 'feedforward-only' templates alone are used. In this work we show how the processing capabilities of optically-realized feedforward-only CNNs can be increased by combining several serial or parallel operations into a single feedforward template. We also derive conditions on a feedforward template whereby the processing resolution in an optical implementation can be increased.

UR - http://www.scopus.com/inward/record.url?scp=0026856464&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026856464&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0026856464

VL - 46

SP - 158

EP - 166

JO - AEU - International Journal of Electronics and Communications

JF - AEU - International Journal of Electronics and Communications

SN - 1434-8411

IS - 3

ER -