Encoding nondeterministic fuzzy tree automata into recursive neural networks
Fuzzy neural systems have been a subject of great interest in the last few years, due to their abilities to facilitate the exchange of information between symbolic and subsymbolic domains. However, the models in the literature are not able to deal with structured organization of information, that is...
Uloženo v:
| Vydáno v: | IEEE transactions on neural networks Ročník 15; číslo 6; s. 1435 - 1449 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
IEEE
01.11.2004
|
| Témata: | |
| ISSN: | 1045-9227 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Fuzzy neural systems have been a subject of great interest in the last few years, due to their abilities to facilitate the exchange of information between symbolic and subsymbolic domains. However, the models in the literature are not able to deal with structured organization of information, that is typically required by symbolic processing. In many application domains, the patterns are not only structured, but a fuzziness degree is attached to each subsymbolic pattern primitive. The purpose of this paper is to show how recursive neural networks, properly conceived for dealing with structured information, can represent nondeterministic fuzzy frontier-to-root tree automata. Whereas available prior knowledge expressed in terms of fuzzy state transition rules are injected into a recursive network, unknown rules are supposed to be filled in by data-driven learning. We also prove the stability of the encoding algorithm, extending previous results on the injection of fuzzy finite-state dynamics in high-order recurrent networks. |
|---|---|
| AbstractList | Fuzzy neural systems have been a subject of great interest in the last few years, due to their abilities to facilitate the exchange of information between symbolic and subsymbolic domains. However, the models in the literature are not able to deal with structured organization of information, that is typically required by symbolic processing. In many application domains, the patterns are not only structured, but a fuzziness degree is attached to each subsymbolic pattern primitive. The purpose of this paper is to show how recursive neural networks, properly conceived for dealing with structured information, can represent nondeterministic fuzzy frontier-to-root tree automata. Whereas available prior knowledge expressed in terms of fuzzy state transition rules are injected into a recursive network, unknown rules are supposed to be filled in by data-driven learning. We also prove the stability of the encoding algorithm, extending previous results on the injection of fuzzy finite-state dynamics in high-order recurrent networks. Fuzzy neural systems have been a subject of great interest in the last few years, due to their abilities to facilitate the exchange of information between symbolic and subsymbolic domains. However, the models in the literature are not able to deal with structured organization of information, that is typically required by symbolic processing. In many application domains, the patterns are not only structured, but a fuzziness degree is attached to each subsymbolic pattern primitive. The purpose of this paper is to show how recursive neural networks, properly conceived for dealing with structured information, can represent nondeterministic fuzzy frontier-to-root tree automata. Whereas available prior knowledge expressed in terms of fuzzy state transition rules are injected into a recursive network, unknown rules are supposed to be filled in by data-driven learning. We also prove the stability of the encoding algorithm, extending previous results on the injection of fuzzy finite-state dynamics in high-order recurrent networks.Fuzzy neural systems have been a subject of great interest in the last few years, due to their abilities to facilitate the exchange of information between symbolic and subsymbolic domains. However, the models in the literature are not able to deal with structured organization of information, that is typically required by symbolic processing. In many application domains, the patterns are not only structured, but a fuzziness degree is attached to each subsymbolic pattern primitive. The purpose of this paper is to show how recursive neural networks, properly conceived for dealing with structured information, can represent nondeterministic fuzzy frontier-to-root tree automata. Whereas available prior knowledge expressed in terms of fuzzy state transition rules are injected into a recursive network, unknown rules are supposed to be filled in by data-driven learning. We also prove the stability of the encoding algorithm, extending previous results on the injection of fuzzy finite-state dynamics in high-order recurrent networks. |
| Author | Petrosino, A. Gori, M. |
| Author_xml | – sequence: 1 givenname: M. surname: Gori fullname: Gori, M. organization: Dipt. di Ingegneria dell'Informazione, Univ. di Siena, Italy – sequence: 2 givenname: A. surname: Petrosino fullname: Petrosino, A. |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/15565771$$D View this record in MEDLINE/PubMed |
| BookMark | eNqF0b1v1TAUBXAPRfQDZgYklAmm9-ob27E9oqp8SE9lKbN149wgQ2IX26Fq_3ry9ApISNDpLr9zJPucsqOYIjH2AvgWgNvz66urbcu53BqhlVFH7AS4VBvbtvqYnZbylXOQindP2TEo1Smt4YTtLqNPQ4hfmrVtoEp5DjGUGnwzLvf3d03NRA0uNc1YsQmxpiaTX3IJP6iJtGSc1lNvU_5WnrEnI06Fnj_cM_b53eX1xYfN7tP7jxdvdxsvhawbA-Og9OB7041oW4tcE--tHbTnGtFTPwg5dArQStm3YBEBSFo_CoHKoDhjbw69Nzl9X6hUN4fiaZowUlqKsxy69dmdXuXr_8pOAxe2M4_C1gijQfFHIWihQfM9fPUAl36mwd3kMGO-c7_-fgXqAHxOpWQanQ8Va0ixZgyTA-72u7p1V7ff1R12XXPnf-V-V_8z8fKQCET0RwslWsPFT77-r7E |
| CODEN | ITNNEP |
| CitedBy_id | crossref_primary_10_1051_ita_2018004 crossref_primary_10_3233_JIFS_221960 crossref_primary_10_1016_j_imavis_2006_01_022 crossref_primary_10_1109_TNN_2005_863472 crossref_primary_10_1016_j_ins_2011_12_024 crossref_primary_10_1007_s00500_012_0856_y crossref_primary_10_1016_j_patcog_2006_02_004 crossref_primary_10_1016_j_patrec_2020_07_032 crossref_primary_10_1016_j_patrec_2018_05_004 crossref_primary_10_3233_JIFS_201298 crossref_primary_10_1016_j_neucom_2008_10_021 |
| Cites_doi | 10.1109/TSMC.1986.289310 10.1007/978-1-4615-2247-8 10.1007/978-1-4757-0450-1 10.1109/IJCNN.1991.155350 10.1109/EDAC.1990.136721 10.1016/s0893-6080(96)00105-0 10.1109/TSMC.1973.5408583 10.1145/235809.235811 10.1016/S0031-3203(97)00021-6 10.1109/72.572108 10.1109/69.917555 10.1016/B978-0-12-775260-0.50018-9 10.1016/0031-3203(73)90028-9 10.1007/BF00116897 10.1162/neco.1996.8.4.675 10.1016/0262-8856(95)97285-T 10.1109/TNN.1994.8753425 10.1109/72.809076 10.1109/72.712151 10.1109/91.660809 10.1109/TPAMI.1985.4767725 10.1364/AO.26.004972 10.1109/ijcnn.1998.682247 10.1016/0950-7051(96)81916-2 |
| ContentType | Journal Article |
| DBID | RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QO 8FD FR3 P64 7SC JQ2 L7M L~C L~D 7X8 |
| DOI | 10.1109/TNN.2004.837585 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Biotechnology Research Abstracts Technology Research Database Engineering Research Database Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Engineering Research Database Biotechnology Research Abstracts Technology Research Database Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional MEDLINE - Academic |
| DatabaseTitleList | Computer and Information Systems Abstracts MEDLINE - Academic Engineering Research Database MEDLINE Engineering Research Database |
| 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: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Anatomy & Physiology Computer Science |
| EndPage | 1449 |
| ExternalDocumentID | 15565771 10_1109_TNN_2004_837585 1353280 |
| Genre | orig-research Comparative Study Evaluation Studies Research Support, Non-U.S. Gov't Journal Article |
| GroupedDBID | --- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG ACGFS AETIX AGQYO AGSQL AHBIQ AI. AIBXA ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS S10 TAE TN5 VH1 AAYXX CITATION AAYOK CGR CUY CVF ECM EIF NPM PKN RIG Z5M 7QO 8FD FR3 P64 7SC JQ2 L7M L~C L~D 7X8 |
| ID | FETCH-LOGICAL-c434t-81fd57dcb86fa929a07e0b99d7c07aacebd34d651a944b219aa11e49cf33a58a3 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 15 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000224929600008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1045-9227 |
| IngestDate | Tue Oct 07 10:15:27 EDT 2025 Fri Sep 05 04:40:41 EDT 2025 Fri Sep 05 05:21:01 EDT 2025 Tue Oct 07 09:22:13 EDT 2025 Wed Feb 19 01:38:08 EST 2025 Sat Nov 29 08:06:03 EST 2025 Tue Nov 18 22:36:05 EST 2025 Tue Aug 26 16:40:04 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 6 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c434t-81fd57dcb86fa929a07e0b99d7c07aacebd34d651a944b219aa11e49cf33a58a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Article-2 ObjectType-Feature-1 ObjectType-Undefined-3 |
| PMID | 15565771 |
| PQID | 17371700 |
| PQPubID | 23462 |
| PageCount | 15 |
| ParticipantIDs | proquest_miscellaneous_17371700 crossref_citationtrail_10_1109_TNN_2004_837585 proquest_miscellaneous_901692267 proquest_miscellaneous_67103968 crossref_primary_10_1109_TNN_2004_837585 proquest_miscellaneous_28387150 pubmed_primary_15565771 ieee_primary_1353280 |
| PublicationCentury | 2000 |
| PublicationDate | 2004-11-01 |
| PublicationDateYYYYMMDD | 2004-11-01 |
| PublicationDate_xml | – month: 11 year: 2004 text: 2004-11-01 day: 01 |
| PublicationDecade | 2000 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transactions on neural networks |
| PublicationTitleAbbrev | TNN |
| PublicationTitleAlternate | IEEE Trans Neural Netw |
| PublicationYear | 2004 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref35 ref15 ref37 ref14 ref36 ref31 ref30 ref33 ref10 Matescu (ref25) 1995; 1 Mizumoto (ref27) 1970; 1 ref2 ref1 Sima (ref34) 1997; 7 ref39 Fu (ref12) 1976 ref16 ref18 Schmitt (ref32) Hopcroft (ref19) 1979 Kuchler (ref23) 1998 Dubois (ref6) 1980; 144 Francesconi (ref7) Goller (ref17) 1997 ref26 ref20 ref22 Fu (ref11) 1974 ref28 Thacher (ref38) 1973 Gèsceg (ref13) 1984 Jang (ref21) 1997 ref29 ref8 ref9 ref4 ref3 ref5 Lin (ref24) 1996 |
| References_xml | – ident: ref31 doi: 10.1109/TSMC.1986.289310 – ident: ref33 doi: 10.1007/978-1-4615-2247-8 – volume-title: Neural Fuzzy Systems year: 1996 ident: ref24 – volume-title: Introduction to Automata Theory, Languages and Computation year: 1979 ident: ref19 – ident: ref1 doi: 10.1007/978-1-4757-0450-1 – ident: ref14 doi: 10.1109/IJCNN.1991.155350 – ident: ref26 doi: 10.1109/EDAC.1990.136721 – volume-title: Proc. 5th Int. Workshop Fuzzy-Neuro Systems ’98 ident: ref32 article-title: Relating chemical structure to activity: An application of the neural folding architecture – ident: ref36 doi: 10.1016/s0893-6080(96)00105-0 – ident: ref37 doi: 10.1109/TSMC.1973.5408583 – volume-title: A connectionist approach for learning search-control heuristics for automated deduction systems year: 1997 ident: ref17 – ident: ref28 doi: 10.1145/235809.235811 – ident: ref3 doi: 10.1016/S0031-3203(97)00021-6 – ident: ref35 doi: 10.1109/72.572108 – volume: 1 start-page: 292 issue: 5 year: 1995 ident: ref25 article-title: Lexical analysis with a simple finite-fuzzy-automaton model publication-title: J. Univ. Comput. Sci. – ident: ref4 doi: 10.1109/69.917555 – ident: ref20 doi: 10.1016/B978-0-12-775260-0.50018-9 – start-page: 144 volume-title: Proc. 2nd IAPR Workshop Graphics Recognition ident: ref7 article-title: Logo recognition by recursive neural networks – volume: 7 start-page: 679 year: 1997 ident: ref34 article-title: Analog stable simulation of discrete neural networks publication-title: Neural Netw. World – ident: ref39 doi: 10.1016/0031-3203(73)90028-9 – start-page: 143 volume-title: Currents in the Theory of Computing year: 1973 ident: ref38 article-title: Tree automata: An informal survey – ident: ref9 doi: 10.1007/BF00116897 – ident: ref29 doi: 10.1162/neco.1996.8.4.675 – volume: 144 start-page: 220 volume-title: Fuzzy Sets and Systems: Theory and Applications year: 1980 ident: ref6 – volume-title: Tree Automata year: 1984 ident: ref13 – ident: ref5 doi: 10.1016/0262-8856(95)97285-T – ident: ref15 doi: 10.1109/TNN.1994.8753425 – volume-title: On the correspondence between neural folding architectures and tree automata year: 1998 ident: ref23 – ident: ref18 doi: 10.1109/72.809076 – ident: ref10 doi: 10.1109/72.712151 – ident: ref30 doi: 10.1109/91.660809 – volume: 1 start-page: 87 year: 1970 ident: ref27 article-title: Fuzzy languages publication-title: Syst. Comput. Controls – volume-title: Neuro-Fuzzy and Soft Computing year: 1997 ident: ref21 – ident: ref22 doi: 10.1109/TPAMI.1985.4767725 – ident: ref16 doi: 10.1364/AO.26.004972 – ident: ref2 doi: 10.1109/ijcnn.1998.682247 – ident: ref8 doi: 10.1016/0950-7051(96)81916-2 – volume-title: Syntactic Methods in Pattern Recognition year: 1974 ident: ref11 – volume-title: Springer-Verlag year: 1976 ident: ref12 |
| SSID | ssj0014506 |
| Score | 1.8440095 |
| Snippet | Fuzzy neural systems have been a subject of great interest in the last few years, due to their abilities to facilitate the exchange of information between... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1435 |
| SubjectTerms | Algorithms Application software Artificial Intelligence Computer Simulation Councils Decision Support Techniques Encoding Feedback Fuzzy Logic Fuzzy neural networks Fuzzy sets Fuzzy systems fuzzy tree automata knowledge representation Learning automata Logistic Models Neural networks Neural Networks (Computer) Pattern recognition Pattern Recognition, Automated - methods Production recursive neural networks |
| Title | Encoding nondeterministic fuzzy tree automata into recursive neural networks |
| URI | https://ieeexplore.ieee.org/document/1353280 https://www.ncbi.nlm.nih.gov/pubmed/15565771 https://www.proquest.com/docview/17371700 https://www.proquest.com/docview/28387150 https://www.proquest.com/docview/67103968 https://www.proquest.com/docview/901692267 |
| Volume | 15 |
| WOSCitedRecordID | wos000224929600008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) issn: 1045-9227 databaseCode: RIE dateStart: 19900101 customDbUrl: isFulltext: true dateEnd: 20111231 titleUrlDefault: https://ieeexplore.ieee.org/ omitProxy: false ssIdentifier: ssj0014506 providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VigMcKOzySIHiA0IcyDaOndg-VqgVB7TiUKS9RbZjS5UgqXYTpPbXd2xntyCxSNxymCQjzUw8r3wfwHvjqS08L3InRZtzozGkHK_ykFs76m1pWSKbEMulXK3UtwP4tPsXxjkXl8_cIlzGWX7b2zG0yk4DR0MpsUB_IESd_tXaTQx4FXk0sbrAF5WlmGB8aKFOL5fLWAgusBjD7Dgy8YRpn6B_HEaRXWV_ohkPnIuj_1P1KTyZEktyljzhGRy4bgbzsw6L6p835AOJq56xhz6Doy2XA5lCewaPfwMmnMPX88724VQjXd-108ZMhHQmfry9vSFhlk30iM_WgyZX3dCTdejch2V4EjAyUZUubZhvnsP3i_PLz1_yiXcht5zxIZfUt5VorZG115g-6UK4wijVClsIra0zLeNtXVGtODf4ydOaUseV9YzpSmr2Ag5RO_cKiKfMMNV6gw7AS881Wsl4Jaqy8EY6m8Fia4DGTqDkgRvjRxOLk0I1aLxAlcmbZLwMPu5uuE54HPtF58Eu92LJJBm821q4wVAK8xHduX7cNFQwEeAK90tgLoYFZvUPiVqE2XotMyB7JFTAv8GkV2TwMvnXvYaTWx7_XfPX8CjBTIYG0Bs4HNajewsP7a_harM-waBYyZMYFHdGMglB |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Na9RAFH-UKqgHq7ta41fnIOLBbDOZyU7mWKSl4ho8rNBbmE8o1KTsJkL71_tmkt0quIK3HF6SB--9zPvK7wfwTntqMs-z1JXCplwrDCnHizTk1o56kxs2kE2IqiovLuS3Pfi4_RfGOReXz9wsXMZZvm1NH1plx4GjIS-xQL9XcJ5nw99a25kBLyKTJtYX-Ko8FyOQD83k8bKqYik4w3IM8-PIxRPmfYL-cRxFfpXdqWY8cs4O_k_ZJ_B4TC3JyeALT2HPNROYnjRYVv-4Ie9JXPaMXfQJHGzYHMgY3BN49Bs04RQWp41pw7lGmrax485MBHUmvr-9vSFhmk1Uj89WnSKXTdeSVejdh3V4ElAyUZVm2DFfP4PvZ6fLT-fpyLyQGs54l5bU20JYo8u5V5hAqUy4TEtphcmEUsZpy7idF1RJzjV-9JSi1HFpPGOqKBV7DvuonXsBxFOmmbReowvw3HOFVtJeiiLPvC6dSWC2MUBtRljywI5xVcfyJJM1Gi-QZfJ6MF4CH7Y3XA-IHLtFp8Eud2KDSRI42li4xmAKExLVuLZf11QwEQALd0tgNoYlZvEPibkI0_V5mQDZISEDAg6mvSKBw8G_7jQc3fLl3zU_ggfny6-LevG5-vIKHg6gk6Ed9Br2u1Xv3sB987O7XK_extD4Be3nC6A |
| 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=Encoding+nondeterministic+fuzzy+tree+automata+into+recursive+neural+networks&rft.jtitle=IEEE+transactions+on+neural+networks&rft.au=Gori%2C+Marco&rft.au=Petrosino%2C+Alfredo&rft.date=2004-11-01&rft.issn=1045-9227&rft.volume=15&rft.issue=6&rft.spage=1435&rft_id=info:doi/10.1109%2FTNN.2004.837585&rft_id=info%3Apmid%2F15565771&rft.externalDocID=15565771 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1045-9227&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1045-9227&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1045-9227&client=summon |