Constructing associative memories using neural networks

X. Xu; W. T. Tsai

doi:10.1117/12.951679

Constructing associative memories using neural networks

X. Xu
, W. T. Tsai

University of Minnesota Twin Cities

科研成果: 期刊稿件 › 文章 › 同行评审

摘要

This paper proposes using a generalized Hopfield's model 1, also known as the McCulloh-Pitts model 2, as associative memories. The system always converges to the nearest stored words. This is not true for Hopfield's model. We also determine the information capacity of this generalized model. Our result is better than those in the literature.

源语言	英语
页（从-至）	166-173
页数	8
期刊	Proceedings of SPIE - The International Society for Optical Engineering
卷	1058
DOI	https://doi.org/10.1117/12.951679
出版状态	已出版 - 17 5月 1989
已对外发布	是

访问文件

10.1117/12.951679

其它文件与链接

链接到 Scopus 的出版物

引用此

@article{2cea8a686dcc4b15ac750286829295ce,

title = "Constructing associative memories using neural networks",

abstract = "This paper proposes using a generalized Hopfield's model 1, also known as the McCulloh-Pitts model 2, as associative memories. The system always converges to the nearest stored words. This is not true for Hopfield's model. We also determine the information capacity of this generalized model. Our result is better than those in the literature.",

author = "X. Xu and Tsai, \{W. T.\}",

year = "1989",

month = may,

day = "17",

doi = "10.1117/12.951679",

language = "英语",

volume = "1058",

pages = "166--173",

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

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Constructing associative memories using neural networks

AU - Xu, X.

AU - Tsai, W. T.

PY - 1989/5/17

Y1 - 1989/5/17

N2 - This paper proposes using a generalized Hopfield's model 1, also known as the McCulloh-Pitts model 2, as associative memories. The system always converges to the nearest stored words. This is not true for Hopfield's model. We also determine the information capacity of this generalized model. Our result is better than those in the literature.

AB - This paper proposes using a generalized Hopfield's model 1, also known as the McCulloh-Pitts model 2, as associative memories. The system always converges to the nearest stored words. This is not true for Hopfield's model. We also determine the information capacity of this generalized model. Our result is better than those in the literature.

UR - https://www.scopus.com/pages/publications/84958482346

U2 - 10.1117/12.951679

DO - 10.1117/12.951679

M3 - 文章

AN - SCOPUS:84958482346

SN - 0277-786X

VL - 1058

SP - 166

EP - 173

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

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

ER -

Constructing associative memories using neural networks

摘要

访问文件

其它文件与链接

指纹

引用此