A memory which forgets

G. Parisi

doi:10.1088/0305-4470/19/10/011

A memory which forgets

G. Parisi^*

^*Corresponding author for this work

University of Rome La Sapienza

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

132 Scopus citations

Abstract

The model of Hopfield for a neural network with associative memory is modified by the introduction of a maximum value for the synaptic strength; in this way old patterns are automatically forgotten and the memory recalls only the most recent ones. If the parameters are correctly chosen, the memory never goes into the state of total confusion, characteristic of the Hopfield model.

Original language	English
Article number	011
Pages (from-to)	L617-L620
Journal	Journal of Physics A: Mathematical and Theoretical
Volume	19
Issue number	10
DOIs	https://doi.org/10.1088/0305-4470/19/10/011
State	Published - 1986
Externally published	Yes

Access to Document

10.1088/0305-4470/19/10/011

Cite this

@article{755642f2a4ef4cf29d92e1c4db3c69cb,

title = "A memory which forgets",

abstract = "The model of Hopfield for a neural network with associative memory is modified by the introduction of a maximum value for the synaptic strength; in this way old patterns are automatically forgotten and the memory recalls only the most recent ones. If the parameters are correctly chosen, the memory never goes into the state of total confusion, characteristic of the Hopfield model.",

author = "G. Parisi",

year = "1986",

doi = "10.1088/0305-4470/19/10/011",

language = "英语",

volume = "19",

pages = "L617--L620",

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

issn = "0305-4470",

publisher = "IOP Publishing Ltd.",

number = "10",

}

TY - JOUR

T1 - A memory which forgets

AU - Parisi, G.

PY - 1986

Y1 - 1986

N2 - The model of Hopfield for a neural network with associative memory is modified by the introduction of a maximum value for the synaptic strength; in this way old patterns are automatically forgotten and the memory recalls only the most recent ones. If the parameters are correctly chosen, the memory never goes into the state of total confusion, characteristic of the Hopfield model.

AB - The model of Hopfield for a neural network with associative memory is modified by the introduction of a maximum value for the synaptic strength; in this way old patterns are automatically forgotten and the memory recalls only the most recent ones. If the parameters are correctly chosen, the memory never goes into the state of total confusion, characteristic of the Hopfield model.

UR - https://www.scopus.com/pages/publications/36149035600

U2 - 10.1088/0305-4470/19/10/011

DO - 10.1088/0305-4470/19/10/011

M3 - 文章

AN - SCOPUS:36149035600

SN - 0305-4470

VL - 19

SP - L617-L620

JO - Journal of Physics A: Mathematical and Theoretical

JF - Journal of Physics A: Mathematical and Theoretical

IS - 10

M1 - 011

ER -

A memory which forgets

Abstract

Access to Document

Other files and links

Fingerprint

Cite this