A unipolar shift-invariant associative hamming net

Francis T.S. Yu; Guowen Lu; Chii Maw Uang; Shizhuo Yin; Zhongkong Wu

doi:10.1117/12.169435

A unipolar shift-invariant associative hamming net

Francis T.S. Yu, Guowen Lu, Chii Maw Uang, Shizhuo Yin, Zhongkong Wu

Electrical Engineering

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

Abstract

Aunipolar shift-invariant associative Hamming net is described in this paper. The proposed Hamming net is a threelayer neural network, in which the first layer is a shift-invariant Hamming layer using unipolar interconnection weight matrix (IWM), the second layer is a winner-Take-All layer, and the last layer is a memory-mapping layer. In experiment, a hybrid optical architecture using photorefractive holograms is proposed.

Original language	English (US)
Pages (from-to)	294-301
Number of pages	8
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	2237
DOIs	https://doi.org/10.1117/12.169435
State	Published - Mar 1 1994
Event	Optical Pattern Recognition V 1994 - Orlando, United States Duration: Apr 4 1994 → Apr 8 1994

All Science Journal Classification (ASJC) codes

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

Access to Document

10.1117/12.169435

Cite this

@article{3eb2cfe699844d64a20dbad63e910f39,

title = "A unipolar shift-invariant associative hamming net",

abstract = "Aunipolar shift-invariant associative Hamming net is described in this paper. The proposed Hamming net is a threelayer neural network, in which the first layer is a shift-invariant Hamming layer using unipolar interconnection weight matrix (IWM), the second layer is a winner-Take-All layer, and the last layer is a memory-mapping layer. In experiment, a hybrid optical architecture using photorefractive holograms is proposed.",

author = "Yu, {Francis T.S.} and Guowen Lu and Uang, {Chii Maw} and Shizhuo Yin and Zhongkong Wu",

year = "1994",

month = mar,

day = "1",

doi = "10.1117/12.169435",

language = "English (US)",

volume = "2237",

pages = "294--301",

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

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - A unipolar shift-invariant associative hamming net

AU - Yu, Francis T.S.

AU - Lu, Guowen

AU - Uang, Chii Maw

AU - Yin, Shizhuo

AU - Wu, Zhongkong

PY - 1994/3/1

Y1 - 1994/3/1

N2 - Aunipolar shift-invariant associative Hamming net is described in this paper. The proposed Hamming net is a threelayer neural network, in which the first layer is a shift-invariant Hamming layer using unipolar interconnection weight matrix (IWM), the second layer is a winner-Take-All layer, and the last layer is a memory-mapping layer. In experiment, a hybrid optical architecture using photorefractive holograms is proposed.

AB - Aunipolar shift-invariant associative Hamming net is described in this paper. The proposed Hamming net is a threelayer neural network, in which the first layer is a shift-invariant Hamming layer using unipolar interconnection weight matrix (IWM), the second layer is a winner-Take-All layer, and the last layer is a memory-mapping layer. In experiment, a hybrid optical architecture using photorefractive holograms is proposed.

UR - http://www.scopus.com/inward/record.url?scp=85076801593&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076801593&partnerID=8YFLogxK

U2 - 10.1117/12.169435

DO - 10.1117/12.169435

M3 - Conference article

AN - SCOPUS:85076801593

SN - 0277-786X

VL - 2237

SP - 294

EP - 301

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

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

T2 - Optical Pattern Recognition V 1994

Y2 - 4 April 1994 through 8 April 1994

ER -

A unipolar shift-invariant associative hamming net

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this