Neural networks and physical systems with emergent
collective computational abilities
J. Hopfield. Proceedings of the National Academy of Sciences of the
United States of America, 79 (8):
2554--2558(April 1982)
Abstract
Computational properties of use of biological
organisms or to the construction of computers can
emerge as collective properties of systems having a
large number of simple equivalent components (or
neurons). The physical meaning of content-addressable
memory is described by an appropriate phase space flow
of the state of a system. A model of such a system is
given, based on aspects of neurobiology but readily
adapted to integrated circuits. The collective
properties of this model produce a content-addressable
memory which correctly yields an entire memory from any
subpart of sufficient size. The algorithm for the time
evolution of the state of the system is based on
asynchronous parallel processing. Additional emergent
collective properties include some capacity for
generalization, familiarity recognition,
categorization, error correction, and time sequence
retention. The collective properties are only weakly
sensitive to details of the modeling or the failure of
individual devices.
%0 Journal Article
%1 hopfield-neural-networks-and-1982
%A Hopfield, J. J.
%D 1982
%J Proceedings of the National Academy of Sciences of the
United States of America
%K network neural seminal
%N 8
%P 2554--2558
%T Neural networks and physical systems with emergent
collective computational abilities
%U http://view.ncbi.nlm.nih.gov/pubmed/6953413
%V 79
%X Computational properties of use of biological
organisms or to the construction of computers can
emerge as collective properties of systems having a
large number of simple equivalent components (or
neurons). The physical meaning of content-addressable
memory is described by an appropriate phase space flow
of the state of a system. A model of such a system is
given, based on aspects of neurobiology but readily
adapted to integrated circuits. The collective
properties of this model produce a content-addressable
memory which correctly yields an entire memory from any
subpart of sufficient size. The algorithm for the time
evolution of the state of the system is based on
asynchronous parallel processing. Additional emergent
collective properties include some capacity for
generalization, familiarity recognition,
categorization, error correction, and time sequence
retention. The collective properties are only weakly
sensitive to details of the modeling or the failure of
individual devices.
@article{hopfield-neural-networks-and-1982,
abstract = {{Computational properties of use of biological
organisms or to the construction of computers can
emerge as collective properties of systems having a
large number of simple equivalent components (or
neurons). The physical meaning of content-addressable
memory is described by an appropriate phase space flow
of the state of a system. A model of such a system is
given, based on aspects of neurobiology but readily
adapted to integrated circuits. The collective
properties of this model produce a content-addressable
memory which correctly yields an entire memory from any
subpart of sufficient size. The algorithm for the time
evolution of the state of the system is based on
asynchronous parallel processing. Additional emergent
collective properties include some capacity for
generalization, familiarity recognition,
categorization, error correction, and time sequence
retention. The collective properties are only weakly
sensitive to details of the modeling or the failure of
individual devices.}},
added-at = {2011-06-02T00:22:00.000+0200},
author = {Hopfield, J. J.},
biburl = {https://www.bibsonomy.org/bibtex/2a3074d3b833b6b02b6fc991407e86804/mhwombat},
citeulike-article-id = {8137707},
citeulike-linkout-0 = {http://view.ncbi.nlm.nih.gov/pubmed/6953413]},
citeulike-linkout-1 = {http://www.hubmed.org/display.cgi?uids=6953413]},
file = {:neural_nets/Hopfield_1982__pnas00447-0135.pdf:PDF},
groups = {public},
interhash = {cf60d9bad127184617e0ad10ae86b78b},
intrahash = {a3074d3b833b6b02b6fc991407e86804},
issn = {0027-8424},
journal = {Proceedings of the National Academy of Sciences of the
United States of America},
keywords = {network neural seminal},
month = apr,
number = 8,
pages = {2554--2558},
pmid = {6953413]},
posted-at = {2010-10-28 14:55:59},
priority = {2},
timestamp = {2016-07-12T19:25:30.000+0200},
title = {Neural networks and physical systems with emergent
collective computational abilities},
url = {http://view.ncbi.nlm.nih.gov/pubmed/6953413]},
username = {mhwombat},
volume = 79,
year = 1982
}