Increased storage capacity for hierarchically structured information in a neural network of Ising type

L. B. Ioffet; K. Kühn; J. L. Van Hemmen

doi:10.1088/0305-4470/22/21/012

Increased storage capacity for hierarchically structured information in a neural network of Ising type

L. B. Ioffet, K. Kühn, J. L. Van Hemmen

Research output: Contribution to journal › Letter › peer-review

2 Scopus citations

Abstract

Modelling formal neurons by lsing spins, we describe a simple two-neuron interaction which allows optimal storage capacity for hierarchically structured information. This takes care both of the low-activity limit in simple, Hopfield-type, networks and of the correlations which occur inside the classes of information hierarchies.

Original language	English (US)
Pages (from-to)	L1037, L1041
Journal	Journal of Physics A: Mathematical and General
Volume	22
Issue number	21
DOIs	https://doi.org/10.1088/0305-4470/22/21/012
State	Published - Nov 7 1989
Externally published	Yes

All Science Journal Classification (ASJC) codes

Statistical and Nonlinear Physics
Mathematical Physics
Physics and Astronomy(all)

Access to Document

10.1088/0305-4470/22/21/012

Cite this

@article{af5c468df42e4724bc7e01c0ce065b22,

title = "Increased storage capacity for hierarchically structured information in a neural network of Ising type",

abstract = "Modelling formal neurons by lsing spins, we describe a simple two-neuron interaction which allows optimal storage capacity for hierarchically structured information. This takes care both of the low-activity limit in simple, Hopfield-type, networks and of the correlations which occur inside the classes of information hierarchies.",

author = "Ioffet, {L. B.} and K. K{\"u}hn and {Van Hemmen}, {J. L.}",

year = "1989",

month = nov,

day = "7",

doi = "10.1088/0305-4470/22/21/012",

language = "English (US)",

volume = "22",

pages = "L1037, L1041",

journal = "Journal of Physics A: Mathematical and Theoretical",

issn = "1751-8113",

publisher = "IOP Publishing Ltd.",

number = "21",

}

TY - JOUR

T1 - Increased storage capacity for hierarchically structured information in a neural network of Ising type

AU - Ioffet, L. B.

AU - Kühn, K.

AU - Van Hemmen, J. L.

PY - 1989/11/7

Y1 - 1989/11/7

N2 - Modelling formal neurons by lsing spins, we describe a simple two-neuron interaction which allows optimal storage capacity for hierarchically structured information. This takes care both of the low-activity limit in simple, Hopfield-type, networks and of the correlations which occur inside the classes of information hierarchies.

AB - Modelling formal neurons by lsing spins, we describe a simple two-neuron interaction which allows optimal storage capacity for hierarchically structured information. This takes care both of the low-activity limit in simple, Hopfield-type, networks and of the correlations which occur inside the classes of information hierarchies.

UR - http://www.scopus.com/inward/record.url?scp=36149029826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36149029826&partnerID=8YFLogxK

U2 - 10.1088/0305-4470/22/21/012

DO - 10.1088/0305-4470/22/21/012

M3 - Letter

AN - SCOPUS:36149029826

SN - 1751-8113

VL - 22

SP - L1037, L1041

JO - Journal of Physics A: Mathematical and Theoretical

JF - Journal of Physics A: Mathematical and Theoretical

IS - 21

ER -

Increased storage capacity for hierarchically structured information in a neural network of Ising type

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this