Composite patterns

D. Horn

doi:10.1016/0893-6080(88)90069-X

Composite patterns

D. Horn^*

^*Corresponding author for this work

School of Physics and Astronomy

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

Abstract

We address the question how to construct a composite pattern in terms of elementary patterns within the context of neural-network models. This problem suggests itself when one considers the issue of error correction of letters on a printed page. Given a neural-network which stores in it all letters as elementary patterns it can serve as a tool for this error correction purpose provided it has the additional property of shift-invariance, i.e. it has to be able to recognize the letter at any location on the page. The result can be obtained by a suitable generalization of the Hopfield model.

Original language	English
Pages (from-to)	27
Number of pages	1
Journal	Neural Networks
Volume	1
Issue number	1 SUPPL
DOIs	https://doi.org/10.1016/0893-6080(88)90069-X
State	Published - 1988
Event	International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA Duration: 6 Sep 1988 → 10 Sep 1988

Access to Document

10.1016/0893-6080(88)90069-X

Cite this

@article{4b71871019ca41719d668a47d709bfcf,

title = "Composite patterns",

abstract = "We address the question how to construct a composite pattern in terms of elementary patterns within the context of neural-network models. This problem suggests itself when one considers the issue of error correction of letters on a printed page. Given a neural-network which stores in it all letters as elementary patterns it can serve as a tool for this error correction purpose provided it has the additional property of shift-invariance, i.e. it has to be able to recognize the letter at any location on the page. The result can be obtained by a suitable generalization of the Hopfield model.",

author = "D. Horn",

year = "1988",

doi = "10.1016/0893-6080(88)90069-X",

language = "אנגלית",

volume = "1",

pages = "27",

journal = "Neural Networks",

issn = "0893-6080",

publisher = "Elsevier Ltd.",

number = "1 SUPPL",

note = "International Neural Network Society 1988 First Annual Meeting ; Conference date: 06-09-1988 Through 10-09-1988",

}

TY - JOUR

T1 - Composite patterns

AU - Horn, D.

PY - 1988

Y1 - 1988

N2 - We address the question how to construct a composite pattern in terms of elementary patterns within the context of neural-network models. This problem suggests itself when one considers the issue of error correction of letters on a printed page. Given a neural-network which stores in it all letters as elementary patterns it can serve as a tool for this error correction purpose provided it has the additional property of shift-invariance, i.e. it has to be able to recognize the letter at any location on the page. The result can be obtained by a suitable generalization of the Hopfield model.

AB - We address the question how to construct a composite pattern in terms of elementary patterns within the context of neural-network models. This problem suggests itself when one considers the issue of error correction of letters on a printed page. Given a neural-network which stores in it all letters as elementary patterns it can serve as a tool for this error correction purpose provided it has the additional property of shift-invariance, i.e. it has to be able to recognize the letter at any location on the page. The result can be obtained by a suitable generalization of the Hopfield model.

UR - http://www.scopus.com/inward/record.url?scp=0024177146&partnerID=8YFLogxK

U2 - 10.1016/0893-6080(88)90069-X

DO - 10.1016/0893-6080(88)90069-X

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.conferencearticle???

AN - SCOPUS:0024177146

SN - 0893-6080

VL - 1

SP - 27

JO - Neural Networks

JF - Neural Networks

IS - 1 SUPPL

T2 - International Neural Network Society 1988 First Annual Meeting

Y2 - 6 September 1988 through 10 September 1988

ER -

Composite patterns

Abstract

Access to Document

Other files and links

Fingerprint

Cite this