Content-addressable polychromatic neural net using a specially doped LiNbO3 photorefractive crystal

Francis T. Yu; Shizhuo Yin; Chii Maw Uang

Content-addressable polychromatic neural net using a specially doped LiNbO3 photorefractive crystal

Francis T. Yu, Shizhuo Yin, Chii Maw Uang

Electrical Engineering

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

Abstract

In this paper, a polychromatic neural net using a specially doped LiNbO₃ photorefractive crystal is presented. This neural net is a two-level high-content addressable memory. The first level is a polychromatic Hamming net for color image classification, and the second level is a mapping net, based on a photorefractive crystal associative memory. The major advantage of this neural net must be the large storage capacity and it requires fewer interconnection links. Experimental demonstrations are provided, in which we have shown that the proposed neural net is consistent with the theoretical model.

Original language	English (US)
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Editors	David P. Casasent
Publisher	Publ by Society of Photo-Optical Instrumentation Engineers
Pages	431-441
Number of pages	11
Volume	1959
ISBN (Print)	0819411957
State	Published - Dec 1 1993
Event	Optical Pattern Recognition IV - Orlando, FL, USA Duration: Apr 13 1993 → Apr 14 1993

Other

Other	Optical Pattern Recognition IV
City	Orlando, FL, USA
Period	4/13/93 → 4/14/93

All Science Journal Classification (ASJC) codes

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Cite this

@inproceedings{3707aaab2a84470ba3c46180fb03038f,

title = "Content-addressable polychromatic neural net using a specially doped LiNbO3 photorefractive crystal",

abstract = "In this paper, a polychromatic neural net using a specially doped LiNbO3 photorefractive crystal is presented. This neural net is a two-level high-content addressable memory. The first level is a polychromatic Hamming net for color image classification, and the second level is a mapping net, based on a photorefractive crystal associative memory. The major advantage of this neural net must be the large storage capacity and it requires fewer interconnection links. Experimental demonstrations are provided, in which we have shown that the proposed neural net is consistent with the theoretical model.",

author = "Yu, {Francis T.} and Shizhuo Yin and Uang, {Chii Maw}",

year = "1993",

month = dec,

day = "1",

language = "English (US)",

isbn = "0819411957",

volume = "1959",

pages = "431--441",

editor = "Casasent, {David P.}",

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

publisher = "Publ by Society of Photo-Optical Instrumentation Engineers",

note = "Optical Pattern Recognition IV ; Conference date: 13-04-1993 Through 14-04-1993",

}

Yu, FT, Yin, S & Uang, CM 1993, Content-addressable polychromatic neural net using a specially doped LiNbO3 photorefractive crystal. in DP Casasent (ed.), Proceedings of SPIE - The International Society for Optical Engineering. vol. 1959, Publ by Society of Photo-Optical Instrumentation Engineers, pp. 431-441, Optical Pattern Recognition IV, Orlando, FL, USA, 4/13/93.

Content-addressable polychromatic neural net using a specially doped LiNbO3 photorefractive crystal. / Yu, Francis T.; Yin, Shizhuo; Uang, Chii Maw.
Proceedings of SPIE - The International Society for Optical Engineering. ed. / David P. Casasent. Vol. 1959 Publ by Society of Photo-Optical Instrumentation Engineers, 1993. p. 431-441.

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

TY - GEN

T1 - Content-addressable polychromatic neural net using a specially doped LiNbO3 photorefractive crystal

AU - Yu, Francis T.

AU - Yin, Shizhuo

AU - Uang, Chii Maw

PY - 1993/12/1

Y1 - 1993/12/1

N2 - In this paper, a polychromatic neural net using a specially doped LiNbO3 photorefractive crystal is presented. This neural net is a two-level high-content addressable memory. The first level is a polychromatic Hamming net for color image classification, and the second level is a mapping net, based on a photorefractive crystal associative memory. The major advantage of this neural net must be the large storage capacity and it requires fewer interconnection links. Experimental demonstrations are provided, in which we have shown that the proposed neural net is consistent with the theoretical model.

AB - In this paper, a polychromatic neural net using a specially doped LiNbO3 photorefractive crystal is presented. This neural net is a two-level high-content addressable memory. The first level is a polychromatic Hamming net for color image classification, and the second level is a mapping net, based on a photorefractive crystal associative memory. The major advantage of this neural net must be the large storage capacity and it requires fewer interconnection links. Experimental demonstrations are provided, in which we have shown that the proposed neural net is consistent with the theoretical model.

UR - http://www.scopus.com/inward/record.url?scp=0027875052&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027875052&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027875052

SN - 0819411957

VL - 1959

SP - 431

EP - 441

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

A2 - Casasent, David P.

PB - Publ by Society of Photo-Optical Instrumentation Engineers

T2 - Optical Pattern Recognition IV

Y2 - 13 April 1993 through 14 April 1993

ER -

Content-addressable polychromatic neural net using a specially doped LiNbO3 photorefractive crystal

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this