Improved storage capacity in correlation matrix memories storing fixed weight codes

Stephen John Hobson; Jim Austin

Improved storage capacity in correlation matrix memories storing fixed weight codes

Computer Science

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

Abstract

In this paper we introduce an improved binary correlation matrix memory (CMM) with better storage capacity when storing sparse fixed weight codes generated with the algorithm of Baum et al. We outline associative memory, and describe the binary correlation matrix memory- a specific example of a distributed associative memory. The importance of the representation used in a CMM for input and output codes is discussed, with specific regard to sparse fixed weight codes. We present an algorithm for generating of fixed weight codes, originally given by Baum et al. The properties of this algorithm are briefly discussed, including possible thresholding functions which could be used when storing these codes in a CMM; L-max and L-wta. Finally, results generated from a series of simulations are used to demonstrate that the use of L-wta as a thresholding function provides an increase in storage capacity over L-max.

Original language	English
Title of host publication	Lecture Notes in Computer Science
Place of Publication	ICANN 2009
Publisher	Springer
Pages	728-736
Number of pages	9
Volume	5768
Edition	PART 1
ISBN (Print)	978-3-642-04273-7
Publication status	Published - 16 Sep 2009

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Keywords

associative memory, correlation matrix memory, storage capacity, fixed weight codes, pattern recognition

Access to Document

Improved storage capacity in correlation matrix memories storing fixed weight codesAccepted author manuscript, 205 KB

Cite this

@inproceedings{30b160b8a7b44616a36e2a5052be9ad3,

title = "Improved storage capacity in correlation matrix memories storing fixed weight codes",

abstract = "In this paper we introduce an improved binary correlation matrix memory (CMM) with better storage capacity when storing sparse fixed weight codes generated with the algorithm of Baum et al. We outline associative memory, and describe the binary correlation matrix memory- a specific example of a distributed associative memory. The importance of the representation used in a CMM for input and output codes is discussed, with specific regard to sparse fixed weight codes. We present an algorithm for generating of fixed weight codes, originally given by Baum et al. The properties of this algorithm are briefly discussed, including possible thresholding functions which could be used when storing these codes in a CMM; L-max and L-wta. Finally, results generated from a series of simulations are used to demonstrate that the use of L-wta as a thresholding function provides an increase in storage capacity over L-max.",

keywords = "associative memory, correlation matrix memory, storage capacity, fixed weight codes, pattern recognition",

author = "Hobson, {Stephen John} and Jim Austin",

year = "2009",

month = sep,

day = "16",

language = "English",

isbn = "978-3-642-04273-7",

volume = "5768",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "728--736",

booktitle = "Lecture Notes in Computer Science",

address = "Germany",

edition = "PART 1",

}

TY - GEN

T1 - Improved storage capacity in correlation matrix memories storing fixed weight codes

AU - Hobson, Stephen John

AU - Austin, Jim

PY - 2009/9/16

Y1 - 2009/9/16

N2 - In this paper we introduce an improved binary correlation matrix memory (CMM) with better storage capacity when storing sparse fixed weight codes generated with the algorithm of Baum et al. We outline associative memory, and describe the binary correlation matrix memory- a specific example of a distributed associative memory. The importance of the representation used in a CMM for input and output codes is discussed, with specific regard to sparse fixed weight codes. We present an algorithm for generating of fixed weight codes, originally given by Baum et al. The properties of this algorithm are briefly discussed, including possible thresholding functions which could be used when storing these codes in a CMM; L-max and L-wta. Finally, results generated from a series of simulations are used to demonstrate that the use of L-wta as a thresholding function provides an increase in storage capacity over L-max.

AB - In this paper we introduce an improved binary correlation matrix memory (CMM) with better storage capacity when storing sparse fixed weight codes generated with the algorithm of Baum et al. We outline associative memory, and describe the binary correlation matrix memory- a specific example of a distributed associative memory. The importance of the representation used in a CMM for input and output codes is discussed, with specific regard to sparse fixed weight codes. We present an algorithm for generating of fixed weight codes, originally given by Baum et al. The properties of this algorithm are briefly discussed, including possible thresholding functions which could be used when storing these codes in a CMM; L-max and L-wta. Finally, results generated from a series of simulations are used to demonstrate that the use of L-wta as a thresholding function provides an increase in storage capacity over L-max.

KW - associative memory, correlation matrix memory, storage capacity, fixed weight codes, pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=70350596376&partnerID=8YFLogxK

M3 - Conference contribution

SN - 978-3-642-04273-7

VL - 5768

T3 - Lecture Notes in Computer Science

SP - 728

EP - 736

BT - Lecture Notes in Computer Science

PB - Springer

CY - ICANN 2009

ER -

Improved storage capacity in correlation matrix memories storing fixed weight codes

Abstract

Publication series

Keywords

Access to Document

Other files and links

Cite this