Conundrum of combinatorial complexity

This paper examines fundamental problems underlying difficulties encountered by pattern recognition algorithms, neural networks, and rule systems. These problems are manifested as combinatorial complexity of algorithms, of their computational or training requirements. The paper relates particular ty...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 1998-06, Vol.20 (6), p.666-670
Main Author: Perlovsky, L.I.
Format: Article
Language:English
Subjects:
Adaptive algorithm
Computational complexity
Explosions
Function approximation
Fuzzy logic
History
Mathematics
Neural networks
Neurons
Pattern recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c308t-3b6916384f60e5fbd8ad63a0bb3198f3144f053551b8e3cab6acf64508419e7c3
cites cdi_FETCH-LOGICAL-c308t-3b6916384f60e5fbd8ad63a0bb3198f3144f053551b8e3cab6acf64508419e7c3
container_end_page 670
container_issue 6
container_start_page 666
container_title IEEE transactions on pattern analysis and machine intelligence
container_volume 20
creator Perlovsky, L.I.
description This paper examines fundamental problems underlying difficulties encountered by pattern recognition algorithms, neural networks, and rule systems. These problems are manifested as combinatorial complexity of algorithms, of their computational or training requirements. The paper relates particular types of complexity problems to the roles of a priori knowledge and adaptive learning. Paradigms based on adaptive learning lead to the complexity of training procedures, while nonadaptive rule-based paradigms lead to complexity of rule systems. Model-based approaches to combining adaptivity with a priori knowledge lead to computational complexity. Arguments are presented for the Aristotelian logic being culpable for the difficulty of combining adaptivity and a priority. The potential role of the fuzzy logic in overcoming current difficulties is discussed. Current mathematical difficulties are related to philosophical debates of the past.
doi_str_mv 10.1109/34.683784
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1109_34_683784</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>683784</ieee_id><sourcerecordid>28216797</sourcerecordid><originalsourceid>FETCH-LOGICAL-c308t-3b6916384f60e5fbd8ad63a0bb3198f3144f053551b8e3cab6acf64508419e7c3</originalsourceid><addsrcrecordid>eNqF0E1LxDAQBuAgCtbVg1dPe1Hw0DXTSdLkKItfsOBFzyHJJlBpm5q04P57d-ni1dMwzMPL8BJyDXQFQNUDspWQWEt2QgpQqErkqE5JQUFUpZSVPCcXOX9RCoxTLMjtOvZTv01Tt4xh6WJnm96MMTWmPWxD63-acXdJzoJps786zgX5fH76WL-Wm_eXt_XjpnRI5ViiFQoEShYE9TzYrTRbgYZai6BkQGAsUI6cg5UenbHCuCD2j0gGytcOF-Ruzh1S_J58HnXXZOfb1vQ-TllXsgJRq_p_WDPOa1Ht4f0MXYo5Jx_0kJrOpJ0Gqg-NaWR6bmxvb2bbeO__3PH4CwCjZJc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>27455762</pqid></control><display><type>article</type><title>Conundrum of combinatorial complexity</title><source>IEEE Xplore (Online service)</source><creator>Perlovsky, L.I.</creator><creatorcontrib>Perlovsky, L.I.</creatorcontrib><description>This paper examines fundamental problems underlying difficulties encountered by pattern recognition algorithms, neural networks, and rule systems. These problems are manifested as combinatorial complexity of algorithms, of their computational or training requirements. The paper relates particular types of complexity problems to the roles of a priori knowledge and adaptive learning. Paradigms based on adaptive learning lead to the complexity of training procedures, while nonadaptive rule-based paradigms lead to complexity of rule systems. Model-based approaches to combining adaptivity with a priori knowledge lead to computational complexity. Arguments are presented for the Aristotelian logic being culpable for the difficulty of combining adaptivity and a priority. The potential role of the fuzzy logic in overcoming current difficulties is discussed. Current mathematical difficulties are related to philosophical debates of the past.</description><identifier>ISSN: 0162-8828</identifier><identifier>EISSN: 1939-3539</identifier><identifier>DOI: 10.1109/34.683784</identifier><identifier>CODEN: ITPIDJ</identifier><language>eng</language><publisher>IEEE</publisher><subject>Adaptive algorithm ; Computational complexity ; Explosions ; Function approximation ; Fuzzy logic ; History ; Mathematics ; Neural networks ; Neurons ; Pattern recognition</subject><ispartof>IEEE transactions on pattern analysis and machine intelligence, 1998-06, Vol.20 (6), p.666-670</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c308t-3b6916384f60e5fbd8ad63a0bb3198f3144f053551b8e3cab6acf64508419e7c3</citedby><cites>FETCH-LOGICAL-c308t-3b6916384f60e5fbd8ad63a0bb3198f3144f053551b8e3cab6acf64508419e7c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/683784$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,27903,27904,54774</link.rule.ids></links><search><creatorcontrib>Perlovsky, L.I.</creatorcontrib><title>Conundrum of combinatorial complexity</title><title>IEEE transactions on pattern analysis and machine intelligence</title><addtitle>TPAMI</addtitle><description>This paper examines fundamental problems underlying difficulties encountered by pattern recognition algorithms, neural networks, and rule systems. These problems are manifested as combinatorial complexity of algorithms, of their computational or training requirements. The paper relates particular types of complexity problems to the roles of a priori knowledge and adaptive learning. Paradigms based on adaptive learning lead to the complexity of training procedures, while nonadaptive rule-based paradigms lead to complexity of rule systems. Model-based approaches to combining adaptivity with a priori knowledge lead to computational complexity. Arguments are presented for the Aristotelian logic being culpable for the difficulty of combining adaptivity and a priority. The potential role of the fuzzy logic in overcoming current difficulties is discussed. Current mathematical difficulties are related to philosophical debates of the past.</description><subject>Adaptive algorithm</subject><subject>Computational complexity</subject><subject>Explosions</subject><subject>Function approximation</subject><subject>Fuzzy logic</subject><subject>History</subject><subject>Mathematics</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Pattern recognition</subject><issn>0162-8828</issn><issn>1939-3539</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1998</creationdate><recordtype>article</recordtype><recordid>eNqF0E1LxDAQBuAgCtbVg1dPe1Hw0DXTSdLkKItfsOBFzyHJJlBpm5q04P57d-ni1dMwzMPL8BJyDXQFQNUDspWQWEt2QgpQqErkqE5JQUFUpZSVPCcXOX9RCoxTLMjtOvZTv01Tt4xh6WJnm96MMTWmPWxD63-acXdJzoJps786zgX5fH76WL-Wm_eXt_XjpnRI5ViiFQoEShYE9TzYrTRbgYZai6BkQGAsUI6cg5UenbHCuCD2j0gGytcOF-Ruzh1S_J58HnXXZOfb1vQ-TllXsgJRq_p_WDPOa1Ht4f0MXYo5Jx_0kJrOpJ0Gqg-NaWR6bmxvb2bbeO__3PH4CwCjZJc</recordid><startdate>19980601</startdate><enddate>19980601</enddate><creator>Perlovsky, L.I.</creator><general>IEEE</general><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>19980601</creationdate><title>Conundrum of combinatorial complexity</title><author>Perlovsky, L.I.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c308t-3b6916384f60e5fbd8ad63a0bb3198f3144f053551b8e3cab6acf64508419e7c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1998</creationdate><topic>Adaptive algorithm</topic><topic>Computational complexity</topic><topic>Explosions</topic><topic>Function approximation</topic><topic>Fuzzy logic</topic><topic>History</topic><topic>Mathematics</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Pattern recognition</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Perlovsky, L.I.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Xplore</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Perlovsky, L.I.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Conundrum of combinatorial complexity</atitle><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle><stitle>TPAMI</stitle><date>1998-06-01</date><risdate>1998</risdate><volume>20</volume><issue>6</issue><spage>666</spage><epage>670</epage><pages>666-670</pages><issn>0162-8828</issn><eissn>1939-3539</eissn><coden>ITPIDJ</coden><abstract>This paper examines fundamental problems underlying difficulties encountered by pattern recognition algorithms, neural networks, and rule systems. These problems are manifested as combinatorial complexity of algorithms, of their computational or training requirements. The paper relates particular types of complexity problems to the roles of a priori knowledge and adaptive learning. Paradigms based on adaptive learning lead to the complexity of training procedures, while nonadaptive rule-based paradigms lead to complexity of rule systems. Model-based approaches to combining adaptivity with a priori knowledge lead to computational complexity. Arguments are presented for the Aristotelian logic being culpable for the difficulty of combining adaptivity and a priority. The potential role of the fuzzy logic in overcoming current difficulties is discussed. Current mathematical difficulties are related to philosophical debates of the past.</abstract><pub>IEEE</pub><doi>10.1109/34.683784</doi><tpages>5</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0162-8828
ispartof IEEE transactions on pattern analysis and machine intelligence, 1998-06, Vol.20 (6), p.666-670
issn 0162-8828
1939-3539
language eng
recordid cdi_crossref_primary_10_1109_34_683784
source IEEE Xplore (Online service)
subjects Adaptive algorithm
Computational complexity
Explosions
Function approximation
Fuzzy logic
History
Mathematics
Neural networks
Neurons
Pattern recognition
title Conundrum of combinatorial complexity
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T17%3A25%3A03IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Conundrum%20of%20combinatorial%20complexity&rft.jtitle=IEEE%20transactions%20on%20pattern%20analysis%20and%20machine%20intelligence&rft.au=Perlovsky,%20L.I.&rft.date=1998-06-01&rft.volume=20&rft.issue=6&rft.spage=666&rft.epage=670&rft.pages=666-670&rft.issn=0162-8828&rft.eissn=1939-3539&rft.coden=ITPIDJ&rft_id=info:doi/10.1109/34.683784&rft_dat=%3Cproquest_cross%3E28216797%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c308t-3b6916384f60e5fbd8ad63a0bb3198f3144f053551b8e3cab6acf64508419e7c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=27455762&rft_id=info:pmid/&rft_ieee_id=683784&rfr_iscdi=true