Symbolic functions from neural computation

Is thought computation over ideas? Turing, and many cognitive scientists since, have assumed so, and formulated computational systems in which meaningful concepts are encoded by symbols which are the objects of computation. Cognition has been carved into parts, each a function defined over such symb...

Full description

Saved in:
Bibliographic Details
Published in:Philosophical transactions of the Royal Society of London. Series A: Mathematical, physical, and engineering sciences Vol. 370; no. 1971; p. 3543
Main Author: Smolensky, Paul
Format: Journal Article
Language:English
Published: England 28.07.2012
Subjects:
Biomimetics - methods
Cognition - physiology
Computer Simulation
Humans
Language
Models, Neurological
Nerve Net - physiology
Neural Networks (Computer)
Neurons - physiology
Symbolism
ISSN:1364-503X
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Is thought computation over ideas? Turing, and many cognitive scientists since, have assumed so, and formulated computational systems in which meaningful concepts are encoded by symbols which are the objects of computation. Cognition has been carved into parts, each a function defined over such symbols. This paper reports on a research program aimed at computing these symbolic functions without computing over the symbols. Symbols are encoded as patterns of numerical activation over multiple abstract neurons, each neuron simultaneously contributing to the encoding of multiple symbols. Computation is carried out over the numerical activation values of such neurons, which individually have no conceptual meaning. This is massively parallel numerical computation operating within a continuous computational medium. The paper presents an axiomatic framework for such a computational account of cognition, including a number of formal results. Within the framework, a class of recursive symbolic functions can be computed. Formal languages defined by symbolic rewrite rules can also be specified, the subsymbolic computations producing symbolic outputs that simultaneously display central properties of both facets of human language: universal symbolic grammatical competence and statistical, imperfect performance.
AbstractList Is thought computation over ideas? Turing, and many cognitive scientists since, have assumed so, and formulated computational systems in which meaningful concepts are encoded by symbols which are the objects of computation. Cognition has been carved into parts, each a function defined over such symbols. This paper reports on a research program aimed at computing these symbolic functions without computing over the symbols. Symbols are encoded as patterns of numerical activation over multiple abstract neurons, each neuron simultaneously contributing to the encoding of multiple symbols. Computation is carried out over the numerical activation values of such neurons, which individually have no conceptual meaning. This is massively parallel numerical computation operating within a continuous computational medium. The paper presents an axiomatic framework for such a computational account of cognition, including a number of formal results. Within the framework, a class of recursive symbolic functions can be computed. Formal languages defined by symbolic rewrite rules can also be specified, the subsymbolic computations producing symbolic outputs that simultaneously display central properties of both facets of human language: universal symbolic grammatical competence and statistical, imperfect performance.
Is thought computation over ideas? Turing, and many cognitive scientists since, have assumed so, and formulated computational systems in which meaningful concepts are encoded by symbols which are the objects of computation. Cognition has been carved into parts, each a function defined over such symbols. This paper reports on a research program aimed at computing these symbolic functions without computing over the symbols. Symbols are encoded as patterns of numerical activation over multiple abstract neurons, each neuron simultaneously contributing to the encoding of multiple symbols. Computation is carried out over the numerical activation values of such neurons, which individually have no conceptual meaning. This is massively parallel numerical computation operating within a continuous computational medium. The paper presents an axiomatic framework for such a computational account of cognition, including a number of formal results. Within the framework, a class of recursive symbolic functions can be computed. Formal languages defined by symbolic rewrite rules can also be specified, the subsymbolic computations producing symbolic outputs that simultaneously display central properties of both facets of human language: universal symbolic grammatical competence and statistical, imperfect performance.Is thought computation over ideas? Turing, and many cognitive scientists since, have assumed so, and formulated computational systems in which meaningful concepts are encoded by symbols which are the objects of computation. Cognition has been carved into parts, each a function defined over such symbols. This paper reports on a research program aimed at computing these symbolic functions without computing over the symbols. Symbols are encoded as patterns of numerical activation over multiple abstract neurons, each neuron simultaneously contributing to the encoding of multiple symbols. Computation is carried out over the numerical activation values of such neurons, which individually have no conceptual meaning. This is massively parallel numerical computation operating within a continuous computational medium. The paper presents an axiomatic framework for such a computational account of cognition, including a number of formal results. Within the framework, a class of recursive symbolic functions can be computed. Formal languages defined by symbolic rewrite rules can also be specified, the subsymbolic computations producing symbolic outputs that simultaneously display central properties of both facets of human language: universal symbolic grammatical competence and statistical, imperfect performance.
Author Smolensky, Paul
Author_xml – sequence: 1
  givenname: Paul
  surname: Smolensky
  fullname: Smolensky, Paul
  email: smolensky@jhu.edu
  organization: Cognitive Science Department, Johns Hopkins University, Baltimore, MD 21218, USA. smolensky@jhu.edu
BackLink https://www.ncbi.nlm.nih.gov/pubmed/22711873$$D View this record in MEDLINE/PubMed
BookMark eNo1j0tLxDAUhbMYcR66dSlditCa3KSPLGXwBQMuVHBXbvOAStPUpFnMv7fiuDpwzseBb0tWox8NIVeMFozK5i7EGQugjBWUc7EiG8YrkZeUf67JNsYvukxVCedkDVAz1tR8Q27fjq7zQ68ym0Y1936MmQ3eZaNJAYdMeTelGX-HC3JmcYjm8pQ78vH48L5_zg-vTy_7-0OuykrOuZHaGkDDDXTANGoLgkohu4oKi4iCK1uC7gB5XdeSNbpsOqFRKCiXVsKO3Pz9TsF_JxPn1vVRmWHA0fgUW0aBQUUXgwW9PqGpc0a3U-gdhmP77wc_tiZSPQ
CitedBy_id crossref_primary_10_1177_1367877916671425
crossref_primary_10_1007_s12559_023_10124_9
crossref_primary_10_1080_10407413_2013_810099
crossref_primary_10_1111_cogs_12142
crossref_primary_10_1002_aaai_12065
crossref_primary_10_1080_0952813X_2013_782987
ContentType Journal Article
DBID CGR
CUY
CVF
ECM
EIF
NPM
7X8
DOI 10.1098/rsta.2011.0334
DatabaseName Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
DatabaseTitle MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList MEDLINE
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Engineering
Mathematics
Sciences (General)
Physics
ExternalDocumentID 22711873
Genre Research Support, U.S. Gov't, Non-P.H.S
Research Support, Non-U.S. Gov't
Journal Article
GroupedDBID ---
-~X
0R~
18M
2WC
4.4
5VS
AACGO
AANCE
AAWIL
ABBHK
ABFAN
ABPLY
ABTLG
ABXSQ
ABYWD
ACGFO
ACHIC
ACIWK
ACMTB
ACNCT
ACQIA
ACRPL
ACTMH
ADBBV
ADNMO
ADODI
ADQXQ
ADULT
AEUPB
AEXZC
AFFNX
AFVYC
AGLNM
AGPVY
AIHAF
AJZGM
ALMA_UNASSIGNED_HOLDINGS
ALMYZ
ALRMG
AQVQM
BGBPD
BTFSW
CGR
CUY
CVF
DCCCD
DIK
DQDLB
DSRWC
EBS
ECEWR
ECM
EIF
EJD
F5P
H13
HH5
HQ6
HZ~
IPSME
JAAYA
JBMMH
JENOY
JHFFW
JKQEH
JLS
JLXEF
JMS
JPM
JSG
JST
K-O
KQ8
MRS
MV1
NPM
NSAHA
O9-
OK1
P2P
RRY
SA0
TN5
TR2
V1E
W8F
XSW
YNT
~02
7X8
AGQPQ
ID FETCH-LOGICAL-c569t-e9dfe2ae3e2b21dadf240949b604faaa43cf52db2a3777918d58b4da4c25db292
IEDL.DBID 7X8
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000306172800016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1364-503X
IngestDate Thu Oct 02 09:56:49 EDT 2025
Thu Apr 03 07:02:20 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1971
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c569t-e9dfe2ae3e2b21dadf240949b604faaa43cf52db2a3777918d58b4da4c25db292
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 22711873
PQID 1021260711
PQPubID 23479
ParticipantIDs proquest_miscellaneous_1021260711
pubmed_primary_22711873
PublicationCentury 2000
PublicationDate 2012-Jul-28
20120728
PublicationDateYYYYMMDD 2012-07-28
PublicationDate_xml – month: 07
  year: 2012
  text: 2012-Jul-28
  day: 28
PublicationDecade 2010
PublicationPlace England
PublicationPlace_xml – name: England
PublicationTitle Philosophical transactions of the Royal Society of London. Series A: Mathematical, physical, and engineering sciences
PublicationTitleAlternate Philos Trans A Math Phys Eng Sci
PublicationYear 2012
SSID ssj0011652
Score 2.1984844
SecondaryResourceType review_article
Snippet Is thought computation over ideas? Turing, and many cognitive scientists since, have assumed so, and formulated computational systems in which meaningful...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 3543
SubjectTerms Biomimetics - methods
Cognition - physiology
Computer Simulation
Humans
Language
Models, Neurological
Nerve Net - physiology
Neural Networks (Computer)
Neurons - physiology
Symbolism
Title Symbolic functions from neural computation
URI https://www.ncbi.nlm.nih.gov/pubmed/22711873
https://www.proquest.com/docview/1021260711
Volume 370
WOSCitedRecordID wos000306172800016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEF7UKuhBbX3VFxE8qLC02d089iQiFg-2FHyQW9gneDCtpgr-e3e22-pFELyEJBASZr7dmezMfh9Cp4okRlgaY2KlwcwKgWUKTeOcEc2tSBMvB_R0lw0GeVHwYVhwq0Nb5WxO9BO1HilYI--ABDUBMrT4cvyKQTUKqqtBQmMRNahLZQDVWfFdRYhTr7gT05ThpEuLOWlj3oFtI4HAk4Jo8m_ppQ8zvY3_fuAmWg8JZnQ1RUQTLZiqhdZ-0A66q_6cq7VuoRXfBApnzTDQ6-gssFGfb6GL-88XCeTBEYRAj9II9qREwITpXqS8LIT37zZ67N08XN_iILCAVZLyCTZcW0OEoYZIEmuhLYHfPS7TLnhNMKpsQrQkgmZZxuNcJ7lkWjDnYXeXkx20VI0qs4cimVui8kRZLSDeGW5ibogxyirGZDdro5OZ1UoHYKhKiMqM3uvy225ttDs1fTmeMm2UhGQgh073__D0AVp1_vSttCQ_RA3rhq85QsvqY_Jcvx17ZLjjYNj_Arrtw4I
linkProvider ProQuest
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Symbolic+functions+from+neural+computation&rft.jtitle=Philosophical+transactions+of+the+Royal+Society+of+London.+Series+A%3A+Mathematical%2C+physical%2C+and+engineering+sciences&rft.au=Smolensky%2C+Paul&rft.date=2012-07-28&rft.issn=1364-503X&rft.volume=370&rft.issue=1971&rft.spage=3543&rft_id=info:doi/10.1098%2Frsta.2011.0334&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1364-503X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1364-503X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1364-503X&client=summon