Fast relational learning using bottom clause propositionalization with artificial neural networks

Relational learning can be described as the task of learning first-order logic rules from examples. It has enabled a number of new machine learning applications, e.g. graph mining and link analysis. Inductive Logic Programming (ILP) performs relational learning either directly by manipulating first-...

Full description

Saved in:

Bibliographic Details
Published in:	Machine learning Vol. 94; no. 1; pp. 81 - 104
Main Authors:	França, Manoel V. M., Zaverucha, Gerson, d’Avila Garcez, Artur S.
Format:	Journal Article
Language:	English
Published:	New York Springer US 01.01.2014 Springer Nature B.V
Subjects:	Accuracy Artificial Intelligence Computer Science Control Learning Logic Logic programming Mathematical analysis Mechatronics Natural Language Processing (NLP) Neural networks Relational data bases Robotics Simulation and Modeling Tasks Vectors (mathematics) Relational learning Propositionalization Inductive logic programming Neural-symbolic integration Artificial neural networks
ISSN:	0885-6125, 1573-0565
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Relational learning can be described as the task of learning first-order logic rules from examples. It has enabled a number of new machine learning applications, e.g. graph mining and link analysis. Inductive Logic Programming (ILP) performs relational learning either directly by manipulating first-order rules or through propositionalization, which translates the relational task into an attribute-value learning task by representing subsets of relations as features. In this paper, we introduce a fast method and system for relational learning based on a novel propositionalization called Bottom Clause Propositionalization (BCP). Bottom clauses are boundaries in the hypothesis search space used by ILP systems Progol and Aleph. Bottom clauses carry semantic meaning and can be mapped directly onto numerical vectors, simplifying the feature extraction process. We have integrated BCP with a well-known neural-symbolic system, C-IL 2 P, to perform learning from numerical vectors. C-IL 2 P uses background knowledge in the form of propositional logic programs to build a neural network. The integrated system, which we call CILP++, handles first-order logic knowledge and is available for download from Sourceforge. We have evaluated CILP++ on seven ILP datasets, comparing results with Aleph and a well-known propositionalization method, RSD. The results show that CILP++ can achieve accuracy comparable to Aleph, while being generally faster, BCP achieved statistically significant improvement in accuracy in comparison with RSD when running with a neural network, but BCP and RSD perform similarly when running with C4.5. We have also extended CILP++ to include a statistical feature selection method, mRMR, with preliminary results indicating that a reduction of more than 90 % of features can be achieved with a small loss of accuracy.
AbstractList	Relational learning can be described as the task of learning first-order logic rules from examples. It has enabled a number of new machine learning applications, e.g. graph mining and link analysis. Inductive Logic Programming (ILP) performs relational learning either directly by manipulating first-order rules or through propositionalization, which translates the relational task into an attribute-value learning task by representing subsets of relations as features. In this paper, we introduce a fast method and system for relational learning based on a novel propositionalization called Bottom Clause Propositionalization (BCP). Bottom clauses are boundaries in the hypothesis search space used by ILP systems Progol and Aleph. Bottom clauses carry semantic meaning and can be mapped directly onto numerical vectors, simplifying the feature extraction process. We have integrated BCP with a well-known neural-symbolic system, C-IL super(2)P, to perform learning from numerical vectors. C-IL super(2)P uses background knowledge in the form of propositional logic programs to build a neural network. The integrated system, which we call CILP++, handles first-order logic knowledge and is available for download from Sourceforge. We have evaluated CILP++ on seven ILP datasets, comparing results with Aleph and a well-known propositionalization method, RSD. The results show that CILP++ can achieve accuracy comparable to Aleph, while being generally faster, BCP achieved statistically significant improvement in accuracy in comparison with RSD when running with a neural network, but BCP and RSD perform similarly when running with C4.5. We have also extended CILP++ to include a statistical feature selection method, mRMR, with preliminary results indicating that a reduction of more than 90 % of features can be achieved with a small loss of accuracy. Relational learning can be described as the task of learning first-order logic rules from examples. It has enabled a number of new machine learning applications, e.g. graph mining and link analysis. Inductive Logic Programming (ILP) performs relational learning either directly by manipulating first-order rules or through propositionalization, which translates the relational task into an attribute-value learning task by representing subsets of relations as features. In this paper, we introduce a fast method and system for relational learning based on a novel propositionalization called Bottom Clause Propositionalization (BCP). Bottom clauses are boundaries in the hypothesis search space used by ILP systems Progol and Aleph. Bottom clauses carry semantic meaning and can be mapped directly onto numerical vectors, simplifying the feature extraction process. We have integrated BCP with a well-known neural-symbolic system, C-IL 2 P, to perform learning from numerical vectors. C-IL 2 P uses background knowledge in the form of propositional logic programs to build a neural network. The integrated system, which we call CILP++, handles first-order logic knowledge and is available for download from Sourceforge. We have evaluated CILP++ on seven ILP datasets, comparing results with Aleph and a well-known propositionalization method, RSD. The results show that CILP++ can achieve accuracy comparable to Aleph, while being generally faster, BCP achieved statistically significant improvement in accuracy in comparison with RSD when running with a neural network, but BCP and RSD perform similarly when running with C4.5. We have also extended CILP++ to include a statistical feature selection method, mRMR, with preliminary results indicating that a reduction of more than 90 % of features can be achieved with a small loss of accuracy. Issue Title: Special Issue on Inductive Logic Programming (ILP 2012); Guest Editors: Fabrizio Riguzzi and Filip elezný Relational learning can be described as the task of learning first-order logic rules from examples. It has enabled a number of new machine learning applications, e.g. graph mining and link analysis. Inductive Logic Programming (ILP) performs relational learning either directly by manipulating first-order rules or through propositionalization, which translates the relational task into an attribute-value learning task by representing subsets of relations as features. In this paper, we introduce a fast method and system for relational learning based on a novel propositionalization called Bottom Clause Propositionalization (BCP). Bottom clauses are boundaries in the hypothesis search space used by ILP systems Progol and Aleph. Bottom clauses carry semantic meaning and can be mapped directly onto numerical vectors, simplifying the feature extraction process. We have integrated BCP with a well-known neural-symbolic system, C-IL^sup 2^P, to perform learning from numerical vectors. C-IL^sup 2^P uses background knowledge in the form of propositional logic programs to build a neural network. The integrated system, which we call CILP++, handles first-order logic knowledge and is available for download from Sourceforge. We have evaluated CILP++ on seven ILP datasets, comparing results with Aleph and a well-known propositionalization method, RSD. The results show that CILP++ can achieve accuracy comparable to Aleph, while being generally faster, BCP achieved statistically significant improvement in accuracy in comparison with RSD when running with a neural network, but BCP and RSD perform similarly when running with C4.5. We have also extended CILP++ to include a statistical feature selection method, mRMR, with preliminary results indicating that a reduction of more than 90 % of features can be achieved with a small loss of accuracy.[PUBLICATION ABSTRACT]
Author	d’Avila Garcez, Artur S. Zaverucha, Gerson França, Manoel V. M.
Author_xml	– sequence: 1 givenname: Manoel V. M. surname: França fullname: França, Manoel V. M. email: manoel.franca.1@city.ac.uk, manoel@cos.ufrj.br organization: Universidade Federal do Rio de Janeiro, City University London – sequence: 2 givenname: Gerson surname: Zaverucha fullname: Zaverucha, Gerson organization: Universidade Federal do Rio de Janeiro – sequence: 3 givenname: Artur S. surname: d’Avila Garcez fullname: d’Avila Garcez, Artur S. organization: City University London
BookMark	eNqFkTtPwzAYRS1UJErhB7BFYmEJ-G1nRBUvCYkFZst17OKSxsV2VMGvJ2kYUCVg8becc_3Z9xhM2tBaAM4QvEQQiquEYFXREiJSMlLhEh2AKWKClJBxNgFTKCUrOcLsCByntIIQYi75FOhbnXIRbaOzD61uisbq2Pp2WXRpOBch57AuTKO7ZItNDJuQ_Ij6z51TbH1-LXTM3nnj-4TWdnE38jbEt3QCDp1ukj39njPwcnvzPL8vH5_uHubXj6WhmOWyJrKWdCEMFw7X2EFHuXOMWMEpJZBVhkjDXKU5E9IyXFHjpKmNFQtqLarJDFyMuf2S751NWa19MrZpdGtDlxQSjLAhiv-P0ooSDoXAPXq-h65CF_vXDxSXEmPMqp5CI2ViSClapzbRr3X8UAiqoR819qP6ftTQj0K9I_Yc4_PuR3PUvvnTxKOZ-lvapY0_dvpV-gJOHKfj
CitedBy_id	crossref_primary_10_1007_s10994_024_06543_w crossref_primary_10_1016_j_eswa_2015_04_017 crossref_primary_10_1007_s00521_025_11512_y crossref_primary_10_1017_S1471068422000102 crossref_primary_10_3233_NAI_240740 crossref_primary_10_1007_s10994_018_5746_9 crossref_primary_10_1109_ACCESS_2019_2948081 crossref_primary_10_1016_j_artint_2024_104273 crossref_primary_10_1007_s10994_021_05966_z crossref_primary_10_1093_logcom_exad037 crossref_primary_10_1016_j_ijar_2020_01_003 crossref_primary_10_1080_14459795_2016_1151913 crossref_primary_10_1007_s10458_023_09609_6 crossref_primary_10_1016_j_artint_2024_104108 crossref_primary_10_1007_s00521_024_09960_z crossref_primary_10_1016_j_knosys_2023_110685 crossref_primary_10_1016_j_trc_2021_103010 crossref_primary_10_1002_widm_1391 crossref_primary_10_1016_j_ins_2022_06_073 crossref_primary_10_1007_s10994_024_06556_5 crossref_primary_10_1016_j_jlamp_2021_100719 crossref_primary_10_4018_IJESMA_2020040105 crossref_primary_10_1007_s10994_021_06090_8 crossref_primary_10_1260_2040_2295_6_3_281 crossref_primary_10_1016_j_artint_2021_103649 crossref_primary_10_1016_j_ijar_2024_109206 crossref_primary_10_1109_TKDE_2021_3079836 crossref_primary_10_1007_s13748_019_00186_y crossref_primary_10_1016_j_knosys_2020_105972 crossref_primary_10_1016_j_eswa_2023_119842 crossref_primary_10_1109_TASE_2020_3025871 crossref_primary_10_1016_j_eswa_2020_114263 crossref_primary_10_1190_geo2022_0770_1 crossref_primary_10_3233_NAI_240672 crossref_primary_10_1007_s10994_021_06058_8 crossref_primary_10_1038_s41598_021_04590_0 crossref_primary_10_1016_j_datak_2024_102285 crossref_primary_10_1631_FITEE_2100463 crossref_primary_10_3233_IA_190036 crossref_primary_10_1007_s10994_023_06399_6 crossref_primary_10_1109_ACCESS_2021_3109443
Cites_doi	10.1023/A:1008328630915 10.1145/175247.175256 10.1007/BF03037227 10.1007/s10994-006-5833-1 10.1016/0743-1066(94)90035-3 10.1007/s10994-009-5117-7 10.1016/0893-6080(88)90003-2 10.1007/s10994-010-5208-5 10.1007/s10994-006-5834-0 10.1142/S0219720005001004 10.1007/s10994-007-5029-3 10.1007/BF03037232 10.1145/1090193.1090204 10.1007/978-1-4471-0211-3 10.1007/s10994-010-5196-5 10.1038/nature02236 10.1016/S0893-6080(05)80056-5 10.1016/S0004-3702(00)00077-1 10.1007/978-3-540-68856-3 10.1007/978-3-662-04599-2 10.1209/epl/i1997-00167-2 10.1007/978-3-662-04599-2_11 10.7551/mitpress/5236.001.0001 10.3233/HIS-2005-2403 10.7551/mitpress/7432.001.0001 10.1007/3-540-62927-0 10.1007/978-3-540-78652-8 10.1093/oso/9780198538509.003.0012 10.1613/jair.953
ContentType	Journal Article
Copyright	The Author(s) 2013 The Author(s) 2014
Copyright_xml	– notice: The Author(s) 2013 – notice: The Author(s) 2014
DBID	AAYXX CITATION 3V. 7SC 7XB 88I 8AL 8AO 8FD 8FE 8FG 8FK ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- L7M L~C L~D M0N M2P P5Z P62 PHGZM PHGZT PKEHL PQEST PQGLB PQQKQ PQUKI PRINS Q9U
DOI	10.1007/s10994-013-5392-1
DatabaseName	CrossRef ProQuest Central (Corporate) Computer and Information Systems Abstracts ProQuest Central (purchase pre-March 2016) Science Database (Alumni Edition) Computing Database (Alumni Edition) ProQuest Pharma Collection Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central ProQuest Technology Collection ProQuest One Community College ProQuest Central Korea ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Computing Database Science Database ProQuest advanced technologies & aerospace journals ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic (New) ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic
DatabaseTitle	CrossRef Computer Science Database ProQuest Central Student Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Pharma Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Central Korea ProQuest Central (New) Advanced Technologies Database with Aerospace Advanced Technologies & Aerospace Collection ProQuest Computing ProQuest Science Journals (Alumni Edition) ProQuest Central Basic ProQuest Science Journals ProQuest Computing (Alumni Edition) ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection Computer and Information Systems Abstracts Professional Advanced Technologies & Aerospace Database ProQuest One Academic UKI Edition ProQuest One Academic ProQuest Central (Alumni) ProQuest One Academic (New)
DatabaseTitleList	Computer and Information Systems Abstracts Computer and Information Systems Abstracts Computer Science Database
Database_xml	– sequence: 1 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	1573-0565
EndPage	104
ExternalDocumentID	3158991781 10_1007_s10994_013_5392_1
Genre	Feature
GroupedDBID	-4Z -59 -5G -BR -EM -Y2 -~C -~X .4S .86 .DC .VR 06D 0R~ 0VY 199 1N0 1SB 2.D 203 28- 29M 2J2 2JN 2JY 2KG 2KM 2LR 2P1 2VQ 2~H 30V 3V. 4.4 406 408 409 40D 40E 5GY 5QI 5VS 67Z 6NX 6TJ 78A 88I 8AO 8FE 8FG 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAEWM AAHNG AAIAL AAJBT AAJKR AANZL AAOBN AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDZT ABECU ABFTV ABHLI ABHQN ABIVO ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFS ACGOD ACHSB ACHXU ACKNC ACMDZ ACMLO ACNCT ACOKC ACOMO ACPIV ACZOJ ADHHG ADHIR ADIMF ADINQ ADKNI ADKPE ADMLS ADRFC ADTPH ADURQ ADYFF ADZKW AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFEXP AFGCZ AFKRA AFLOW AFQWF AFWTZ AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN AZQEC B-. BA0 BBWZM BDATZ BENPR BGLVJ BGNMA BPHCQ BSONS CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EBLON EBS EIOEI EJD ESBYG F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ6 GQ7 GQ8 GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IHE IJ- IKXTQ ITG ITH ITM IWAJR IXC IZIGR IZQ I~X I~Y I~Z J-C J0Z JBSCW JCJTX JZLTJ K6V K7- KDC KOV KOW LAK LLZTM M0N M2P M4Y MA- MVM N2Q N9A NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM OVD P19 P2P P62 P9O PF- PQQKQ PROAC PT4 Q2X QF4 QM1 QN7 QO4 QOK QOS R4E R89 R9I RHV RIG RNI RNS ROL RPX RSV RZC RZE S16 S1Z S26 S27 S28 S3B SAP SCJ SCLPG SCO SDH SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TAE TEORI TN5 TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW VXZ W23 W48 WH7 WIP WK8 XJT YLTOR Z45 Z7R Z7S Z7U Z7V Z7W Z7X Z7Y Z7Z Z81 Z83 Z85 Z86 Z87 Z88 Z8M Z8N Z8O Z8P Z8Q Z8R Z8S Z8T Z8U Z8W Z8Z Z91 Z92 ZMTXR AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG ADKFA AEZWR AFDZB AFFHD AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP AMVHM ATHPR AYFIA CITATION PHGZM PHGZT PQGLB 7SC 7XB 8AL 8FD 8FK JQ2 L7M L~C L~D PKEHL PQEST PQUKI PRINS Q9U PUEGO
ID	FETCH-LOGICAL-c425t-d38d84b7c67f2d2f0f46ff53e76443059c38c5f9a6578e5294cf8cdce7b4ee1d3
IEDL.DBID	K7-
ISICitedReferencesCount	76
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000328838500005&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0885-6125
IngestDate	Thu Sep 04 18:37:10 EDT 2025 Thu Sep 04 20:09:33 EDT 2025 Tue Nov 04 19:59:27 EST 2025 Tue Nov 18 20:59:27 EST 2025 Sat Nov 29 01:43:26 EST 2025 Fri Feb 21 02:28:49 EST 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	1
Keywords	Relational learning Propositionalization Inductive logic programming Neural-symbolic integration Artificial neural networks
Language	English
License	http://www.springer.com/tdm
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c425t-d38d84b7c67f2d2f0f46ff53e76443059c38c5f9a6578e5294cf8cdce7b4ee1d3
Notes	SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14 ObjectType-Article-2 content type line 23 ObjectType-Article-1 ObjectType-Feature-2
OpenAccessLink	https://link.springer.com/content/pdf/10.1007%2Fs10994-013-5392-1.pdf
PQID	1468822259
PQPubID	23500
PageCount	24
ParticipantIDs	proquest_miscellaneous_1753544306 proquest_miscellaneous_1494360772 proquest_journals_1468822259 crossref_primary_10_1007_s10994_013_5392_1 crossref_citationtrail_10_1007_s10994_013_5392_1 springer_journals_10_1007_s10994_013_5392_1
PublicationCentury	2000
PublicationDate	20140100 2014-1-00 20140101
PublicationDateYYYYMMDD	2014-01-01
PublicationDate_xml	– month: 1 year: 2014 text: 20140100
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York – name: Dordrecht
PublicationTitle	Machine learning
PublicationTitleAbbrev	Mach Learn
PublicationYear	2014
Publisher	Springer US Springer Nature B.V
Publisher_xml	– name: Springer US – name: Springer Nature B.V
References	Paes, Železný, Zaverucha, Page, Srinivasan (CR42) 2007 Richardson, Domingos (CR48) 2006; 62 Džeroski, Lavrač (CR13) 2001 Caruana, Lawrence, Giles (CR3) 2000 Garcez, Zaverucha (CR14) 1999; 11 Jacobs (CR23) 1988; 1 Paes, Revoredo, Zaverucha, Costa (CR41) 2005 Pitangui, Zaverucha (CR45) 2012 Železný, Lavrač (CR55) 2006; 62 De Raedt (CR9) 2008 Krogel, Wrobel (CR29) 2003 Bain, Muggleton (CR1) 1994; 13 Kramer, Lavrač, Flach, Džeroski (CR28) 2001 Uwents, Monfardini, Blockeel, Gori, Scarselli (CR54) 2011; 82 Garcez, Lamb, Gabbay (CR18) 2008 Rumelhart, Widrow, Lehr (CR50) 1994; 37 Muggleton, Tamaddoni-Nezhad (CR38) 2008; 70 Craven, Shavlik (CR7) 1995 Tamaddoni-Nezhad, Muggleton (CR53) 2009; 76 Kijsirikul, Lerdlamnaochai (CR24) 2005; 2 Lavrač, Džeroski (CR33) 1994 May, Dandy, Maier, Suzuki (CR34) 2011 Perlich, Merugu (CR44) 2005 Møller (CR35) 1993; 6 Guyon, Elisseeff (CR21) 2003; 3 Rumelhart, Hinton, Williams, Rumelhart, McClelland (CR49) 1986 Guillame-Bert, Broda, Garcez (CR20) 2010 Kuželka, Železný (CR31) 2011; 83 Krogel, Rawles, Železný, Flach, Lavrač, Wrobel (CR30) 2003 Quinlan (CR47) 1993 Garcez, Zaverucha (CR15) 2012 Haykin (CR22) 2009 Ding, Peng (CR12) 2005; 3 Srinivasan, Muggleton (CR52) 1994 CR51 Chawla, Bowyer, Hall, Kegelmeyer (CR4) 2002; 16 Garcez, Broda, Gabbay (CR17) 2002 Muggleton (CR36) 1995; 13 DiMaio, Shavlik (CR11) 2004 Paes, Zaverucha, Costa (CR43) 2008 Davis, Burnside, Dutra, Page, Costa (CR8) 2005 King, Srinivasan (CR25) 1995; 13 Garcez, Broda, Gabbay (CR16) 2001; 125 Nienhuys-Cheng, de Wolf (CR40) 1997 Basilio, Zaverucha, Barbosa (CR2) 2001 King, Whelan, Jones, Reiser, Bryant, Muggleton, Kell, Oliver (CR26) 2004; 427 Landwehr, Kersting, De Raedt (CR32) 2007; 8 Koller, Friedman (CR27) 2009 De Raedt, Frasconi, Kersting, Muggleton (CR10) 2008 Muggleton, Paes, Costa, Zaverucha (CR39) 2010 Clark, Niblett (CR5) 1989; 3 Muggleton, De Raedt (CR37) 1994; 19/20 Getoor, Taskar (CR19) 2007 Prechelt (CR46) 1997 Copelli, Eichhorn, Kinouchi, Biehl, Simonetti, Riegler, Caticha (CR6) 1997; 37 M. Bain (5392_CR1) 1994; 13 C. G. Pitangui (5392_CR45) 2012 M. F. Møller (5392_CR35) 1993; 6 A. S. D. Garcez (5392_CR18) 2008 A. Srinivasan (5392_CR52) 1994 S. S. Haykin (5392_CR22) 2009 N. V. Chawla (5392_CR4) 2002; 16 S. H. Nienhuys-Cheng (5392_CR40) 1997 R. Basilio (5392_CR2) 2001 W. Uwents (5392_CR54) 2011; 82 B. Kijsirikul (5392_CR24) 2005; 2 F. DiMaio (5392_CR11) 2004 S. Džeroski (5392_CR13) 2001 A. Paes (5392_CR41) 2005 R. A. Jacobs (5392_CR23) 1988; 1 S. Muggleton (5392_CR36) 1995; 13 5392_CR51 O. Kuželka (5392_CR31) 2011; 83 D. E. Rumelhart (5392_CR49) 1986 R. D. King (5392_CR26) 2004; 427 I. Guyon (5392_CR21) 2003; 3 A. S. D. Garcez (5392_CR15) 2012 A. Paes (5392_CR42) 2007 M. Guillame-Bert (5392_CR20) 2010 S. Muggleton (5392_CR37) 1994; 19/20 F. Železný (5392_CR55) 2006; 62 J. R. Quinlan (5392_CR47) 1993 N. Landwehr (5392_CR32) 2007; 8 J. Davis (5392_CR8) 2005 S. Muggleton (5392_CR38) 2008; 70 S. Muggleton (5392_CR39) 2010 L. Raedt De (5392_CR10) 2008 R. May (5392_CR34) 2011 A. S. D. Garcez (5392_CR16) 2001; 125 A. Paes (5392_CR43) 2008 D. E. Rumelhart (5392_CR50) 1994; 37 R. D. King (5392_CR25) 1995; 13 C. Ding (5392_CR12) 2005; 3 M. A. Krogel (5392_CR29) 2003 A. S. D. Garcez (5392_CR17) 2002 M. Richardson (5392_CR48) 2006; 62 N. Lavrač (5392_CR33) 1994 A. S. D. Garcez (5392_CR14) 1999; 11 L. Prechelt (5392_CR46) 1997 M. A. Krogel (5392_CR30) 2003 S. Kramer (5392_CR28) 2001 R. Caruana (5392_CR3) 2000 M. Copelli (5392_CR6) 1997; 37 D. Koller (5392_CR27) 2009 C. Perlich (5392_CR44) 2005 M. Craven (5392_CR7) 1995 L. Getoor (5392_CR19) 2007 A. Tamaddoni-Nezhad (5392_CR53) 2009; 76 P. Clark (5392_CR5) 1989; 3 L. Raedt De (5392_CR9) 2008
References_xml	– start-page: 286 year: 2012 end-page: 301 ident: CR45 article-title: Learning theories using estimation distribution algorithms and (reduced) bottom clauses publication-title: Proc. ILP – year: 1994 ident: CR33 publication-title: Inductive logic programming: techniques and applications – start-page: 200 year: 2008 end-page: 210 ident: CR43 article-title: Revising first-order logic theories from examples through stochastic local search publication-title: Proc. ILP – year: 2009 ident: CR22 publication-title: Neural networks and learning machines – start-page: 80 year: 2004 end-page: 97 ident: CR11 article-title: Learning an approximation to inductive logic programming clause evaluation publication-title: Proc. ILP – ident: CR51 – volume: 16 start-page: 321 issue: 1 year: 2002 end-page: 357 ident: CR4 article-title: SMOTE: synthetic minority over-sampling technique publication-title: Journal of Artificial Intelligence Research – volume: 11 start-page: 59 year: 1999 end-page: 77 ident: CR14 article-title: The connectionist inductive learning and logic programming system publication-title: Applied Intelligence doi: 10.1023/A:1008328630915 – volume: 37 start-page: 87 issue: 3 year: 1994 end-page: 92 ident: CR50 article-title: The basic ideas in neural networks publication-title: Communications of the ACM doi: 10.1145/175247.175256 – volume: 13 start-page: 245 issue: 3–4 year: 1995 end-page: 286 ident: CR36 article-title: Inverse entailment and Progol publication-title: New Generation Computing doi: 10.1007/BF03037227 – volume: 13 start-page: 291 year: 1994 end-page: 309 ident: CR1 article-title: Learning optimal chess strategies publication-title: Machine Intelligence – year: 2009 ident: CR27 publication-title: Probabilistic graphical models: principles and techniques – start-page: 402 year: 2000 end-page: 408 ident: CR3 article-title: Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping publication-title: Proc. NIPS – year: 1997 ident: CR40 publication-title: Foundations of inductive logic programming – year: 2008 ident: CR10 publication-title: Probabilistic inductive logic programming – start-page: 24 year: 1995 end-page: 30 ident: CR7 article-title: Extracting tree-structured representations of trained networks publication-title: Proc. NIPS – start-page: 318 year: 1986 end-page: 362 ident: CR49 article-title: Learning internal representations by error propagation publication-title: Parallel distributed processing: explorations in the microstructure of cognition – volume: 62 start-page: 107 year: 2006 end-page: 136 ident: CR48 article-title: Markov logic networks publication-title: Machine Learning doi: 10.1007/s10994-006-5833-1 – volume: 3 start-page: 1157 year: 2003 end-page: 1182 ident: CR21 article-title: An introduction to variable and feature selection publication-title: Journal of Machine Learning Research – volume: 3 start-page: 261 year: 1989 end-page: 283 ident: CR5 article-title: The CN2 induction algorithm publication-title: Machine Learning – year: 2008 ident: CR18 publication-title: Neural-symbolic cognitive reasoning – volume: 19/20 start-page: 629 year: 1994 end-page: 679 ident: CR37 article-title: Inductive logic programming: theory and methods publication-title: The Journal of Logic Programming doi: 10.1016/0743-1066(94)90035-3 – volume: 76 start-page: 37 issue: 1 year: 2009 end-page: 72 ident: CR53 article-title: The lattice structure and refinement operators for the hypothesis space bounded by a bottom clause publication-title: Machine Learning doi: 10.1007/s10994-009-5117-7 – volume: 1 start-page: 295 issue: 4 year: 1988 end-page: 307 ident: CR23 article-title: Increased rates of convergence through learning rate adaptation publication-title: Neural Networks doi: 10.1016/0893-6080(88)90003-2 – start-page: 55 year: 1997 end-page: 69 ident: CR46 article-title: Early stopping—but when? publication-title: Neural networks: tricks of the trade – start-page: 217 year: 1994 end-page: 232 ident: CR52 article-title: Mutagenesis: ILP experiments in a non-determinate biological domain publication-title: Proc. ILP – start-page: 379 year: 2007 end-page: 393 ident: CR42 article-title: ILP through propositionalization and stochastic -term DNF learning publication-title: Proc. ILP – volume: 83 start-page: 163 year: 2011 end-page: 192 ident: CR31 article-title: Block-wise construction of tree-like relational features with monotone reducibility and redundancy publication-title: Machine Learning doi: 10.1007/s10994-010-5208-5 – volume: 62 start-page: 33 year: 2006 end-page: 63 ident: CR55 article-title: Propositionalization-based relational subgroup discovery with RSD publication-title: Machine Learning doi: 10.1007/s10994-006-5834-0 – volume: 3 start-page: 185 issue: 2 year: 2005 end-page: 205 ident: CR12 article-title: Minimum redundancy feature selection from microarray gene expression data publication-title: Journal of Bioinformatics and Computational Biology doi: 10.1142/S0219720005001004 – volume: 70 start-page: 121 year: 2008 end-page: 133 ident: CR38 article-title: QG/GA: a stochastic search for Progol publication-title: Machine Learning doi: 10.1007/s10994-007-5029-3 – start-page: 1 year: 2012 end-page: 6 ident: CR15 article-title: Multi-instance learning using recurrent neural networks publication-title: Proc. IJCNN – volume: 13 start-page: 411 issue: 3–4 year: 1995 end-page: 434 ident: CR25 article-title: Relating chemical activity to structure: an examination of ILP successes publication-title: New Generation Computing doi: 10.1007/BF03037232 – start-page: 61 year: 2005 end-page: 67 ident: CR44 article-title: Gene classification: issues and challenges for relational learning publication-title: Proc. 4th international workshop on multi-relational mining doi: 10.1145/1090193.1090204 – volume: 2 start-page: 253 issue: 4 year: 2005 end-page: 267 ident: CR24 article-title: First-order logical neural networks publication-title: International Journal of Hybrid Intelligent Systems – start-page: 84 year: 2005 end-page: 95 ident: CR8 article-title: An integrated approach to learning Bayesian networks of rules publication-title: Proc. ECML – year: 2002 ident: CR17 publication-title: Neural-symbolic learning systems doi: 10.1007/978-1-4471-0211-3 – start-page: 295 year: 2005 end-page: 311 ident: CR41 article-title: Probabilistic first-order theory revision from examples publication-title: Proc. ILP – start-page: 30 year: 2003 end-page: 39 ident: CR29 article-title: Facets of aggregation approaches to propositionalization publication-title: Proc. ILP – year: 1993 ident: CR47 publication-title: C4.5: programs for machine learning – volume: 82 start-page: 315 issue: 3 year: 2011 end-page: 349 ident: CR54 article-title: Neural networks for relational learning: an experimental comparison publication-title: Machine Learning doi: 10.1007/s10994-010-5196-5 – volume: 427 start-page: 247 issue: 6971 year: 2004 end-page: 252 ident: CR26 article-title: Functional genomic hypothesis generation and experimentation by a robot scientist publication-title: Nature doi: 10.1038/nature02236 – start-page: 19 year: 2011 end-page: 44 ident: CR34 article-title: Review of input variable selection methods for artificial neural networks publication-title: Artificial neural networks—methodological advances and biomedical applications – volume: 6 start-page: 525 issue: 4 year: 1993 end-page: 533 ident: CR35 article-title: A scaled conjugate gradient algorithm for fast supervised learning publication-title: Neural Networks doi: 10.1016/S0893-6080(05)80056-5 – start-page: 123 year: 2010 end-page: 130 ident: CR39 article-title: Chess revision: acquiring the rules of chess variants through FOL theory revision from examples publication-title: Proc. ILP – volume: 125 start-page: 155 issue: 1–2 year: 2001 end-page: 207 ident: CR16 article-title: Symbolic knowledge extraction from trained neural networks: a sound approach publication-title: Artificial Intelligence doi: 10.1016/S0004-3702(00)00077-1 – year: 2007 ident: CR19 publication-title: Introduction to statistical relational learning – start-page: 402 year: 2001 end-page: 408 ident: CR2 article-title: Learning logic programs with neural networks publication-title: Proc. ILP – year: 2008 ident: CR9 publication-title: Logical and relational learning doi: 10.1007/978-3-540-68856-3 – year: 2001 ident: CR13 publication-title: Relational data mining doi: 10.1007/978-3-662-04599-2 – volume: 8 start-page: 481 year: 2007 end-page: 507 ident: CR32 article-title: Integrating naive Bayes and FOIL publication-title: Journal of Machine Learning Research – start-page: 197 year: 2003 end-page: 214 ident: CR30 article-title: Comparative evaluation of approaches to propositionalization publication-title: Proc. ILP – start-page: 1 year: 2010 end-page: 8 ident: CR20 article-title: First-order logic learning in artificial neural networks publication-title: Proc. IJCNN – volume: 37 start-page: 427 issue: 6 year: 1997 end-page: 432 ident: CR6 article-title: Noise robustness in multilayer neural networks publication-title: Europhysics Letters doi: 10.1209/epl/i1997-00167-2 – start-page: 262 year: 2001 end-page: 291 ident: CR28 article-title: Propositionalization approaches to relational data mining publication-title: Relational data mining doi: 10.1007/978-3-662-04599-2_11 – volume: 125 start-page: 155 issue: 1–2 year: 2001 ident: 5392_CR16 publication-title: Artificial Intelligence doi: 10.1016/S0004-3702(00)00077-1 – start-page: 24 volume-title: Proc. NIPS year: 1995 ident: 5392_CR7 – volume-title: Neural networks and learning machines year: 2009 ident: 5392_CR22 – volume-title: C4.5: programs for machine learning year: 1993 ident: 5392_CR47 – start-page: 84 volume-title: Proc. ECML year: 2005 ident: 5392_CR8 – volume: 8 start-page: 481 year: 2007 ident: 5392_CR32 publication-title: Journal of Machine Learning Research – volume: 13 start-page: 245 issue: 3–4 year: 1995 ident: 5392_CR36 publication-title: New Generation Computing doi: 10.1007/BF03037227 – start-page: 1 volume-title: Proc. IJCNN year: 2012 ident: 5392_CR15 – start-page: 286 volume-title: Proc. ILP year: 2012 ident: 5392_CR45 – ident: 5392_CR51 – volume: 37 start-page: 427 issue: 6 year: 1997 ident: 5392_CR6 publication-title: Europhysics Letters doi: 10.1209/epl/i1997-00167-2 – volume: 76 start-page: 37 issue: 1 year: 2009 ident: 5392_CR53 publication-title: Machine Learning doi: 10.1007/s10994-009-5117-7 – volume-title: Neural-symbolic cognitive reasoning year: 2008 ident: 5392_CR18 – volume-title: Relational data mining year: 2001 ident: 5392_CR13 doi: 10.1007/978-3-662-04599-2 – start-page: 379 volume-title: Proc. ILP year: 2007 ident: 5392_CR42 – volume: 11 start-page: 59 year: 1999 ident: 5392_CR14 publication-title: Applied Intelligence doi: 10.1023/A:1008328630915 – start-page: 318 volume-title: Parallel distributed processing: explorations in the microstructure of cognition year: 1986 ident: 5392_CR49 doi: 10.7551/mitpress/5236.001.0001 – volume: 37 start-page: 87 issue: 3 year: 1994 ident: 5392_CR50 publication-title: Communications of the ACM doi: 10.1145/175247.175256 – start-page: 1 volume-title: Proc. IJCNN year: 2010 ident: 5392_CR20 – volume: 2 start-page: 253 issue: 4 year: 2005 ident: 5392_CR24 publication-title: International Journal of Hybrid Intelligent Systems doi: 10.3233/HIS-2005-2403 – volume-title: Introduction to statistical relational learning year: 2007 ident: 5392_CR19 doi: 10.7551/mitpress/7432.001.0001 – volume: 427 start-page: 247 issue: 6971 year: 2004 ident: 5392_CR26 publication-title: Nature doi: 10.1038/nature02236 – start-page: 262 volume-title: Relational data mining year: 2001 ident: 5392_CR28 doi: 10.1007/978-3-662-04599-2_11 – start-page: 30 volume-title: Proc. ILP year: 2003 ident: 5392_CR29 – volume: 6 start-page: 525 issue: 4 year: 1993 ident: 5392_CR35 publication-title: Neural Networks doi: 10.1016/S0893-6080(05)80056-5 – volume: 19/20 start-page: 629 year: 1994 ident: 5392_CR37 publication-title: The Journal of Logic Programming doi: 10.1016/0743-1066(94)90035-3 – volume: 70 start-page: 121 year: 2008 ident: 5392_CR38 publication-title: Machine Learning doi: 10.1007/s10994-007-5029-3 – start-page: 123 volume-title: Proc. ILP year: 2010 ident: 5392_CR39 – start-page: 295 volume-title: Proc. ILP year: 2005 ident: 5392_CR41 – volume: 62 start-page: 33 year: 2006 ident: 5392_CR55 publication-title: Machine Learning doi: 10.1007/s10994-006-5834-0 – start-page: 402 volume-title: Proc. NIPS year: 2000 ident: 5392_CR3 – start-page: 80 volume-title: Proc. ILP year: 2004 ident: 5392_CR11 – start-page: 402 volume-title: Proc. ILP year: 2001 ident: 5392_CR2 – volume-title: Foundations of inductive logic programming year: 1997 ident: 5392_CR40 doi: 10.1007/3-540-62927-0 – start-page: 61 volume-title: Proc. 4th international workshop on multi-relational mining year: 2005 ident: 5392_CR44 doi: 10.1145/1090193.1090204 – volume-title: Probabilistic graphical models: principles and techniques year: 2009 ident: 5392_CR27 – start-page: 197 volume-title: Proc. ILP year: 2003 ident: 5392_CR30 – start-page: 19 volume-title: Artificial neural networks—methodological advances and biomedical applications year: 2011 ident: 5392_CR34 – volume-title: Inductive logic programming: techniques and applications year: 1994 ident: 5392_CR33 – volume-title: Probabilistic inductive logic programming year: 2008 ident: 5392_CR10 doi: 10.1007/978-3-540-78652-8 – volume: 13 start-page: 411 issue: 3–4 year: 1995 ident: 5392_CR25 publication-title: New Generation Computing doi: 10.1007/BF03037232 – volume: 1 start-page: 295 issue: 4 year: 1988 ident: 5392_CR23 publication-title: Neural Networks doi: 10.1016/0893-6080(88)90003-2 – start-page: 55 volume-title: Neural networks: tricks of the trade year: 1997 ident: 5392_CR46 – volume: 83 start-page: 163 year: 2011 ident: 5392_CR31 publication-title: Machine Learning doi: 10.1007/s10994-010-5208-5 – volume: 3 start-page: 261 year: 1989 ident: 5392_CR5 publication-title: Machine Learning – volume: 13 start-page: 291 year: 1994 ident: 5392_CR1 publication-title: Machine Intelligence doi: 10.1093/oso/9780198538509.003.0012 – volume: 3 start-page: 1157 year: 2003 ident: 5392_CR21 publication-title: Journal of Machine Learning Research – volume-title: Logical and relational learning year: 2008 ident: 5392_CR9 doi: 10.1007/978-3-540-68856-3 – volume-title: Neural-symbolic learning systems year: 2002 ident: 5392_CR17 doi: 10.1007/978-1-4471-0211-3 – volume: 82 start-page: 315 issue: 3 year: 2011 ident: 5392_CR54 publication-title: Machine Learning doi: 10.1007/s10994-010-5196-5 – start-page: 200 volume-title: Proc. ILP year: 2008 ident: 5392_CR43 – volume: 62 start-page: 107 year: 2006 ident: 5392_CR48 publication-title: Machine Learning doi: 10.1007/s10994-006-5833-1 – start-page: 217 volume-title: Proc. ILP year: 1994 ident: 5392_CR52 – volume: 16 start-page: 321 issue: 1 year: 2002 ident: 5392_CR4 publication-title: Journal of Artificial Intelligence Research doi: 10.1613/jair.953 – volume: 3 start-page: 185 issue: 2 year: 2005 ident: 5392_CR12 publication-title: Journal of Bioinformatics and Computational Biology doi: 10.1142/S0219720005001004
SSID	ssj0002686
Score	2.4608655
Snippet	Relational learning can be described as the task of learning first-order logic rules from examples. It has enabled a number of new machine learning... Issue Title: Special Issue on Inductive Logic Programming (ILP 2012); Guest Editors: Fabrizio Riguzzi and Filip elezný Relational learning can be described as...
SourceID	proquest crossref springer
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	81
SubjectTerms	Accuracy Artificial Intelligence Computer Science Control Learning Logic Logic programming Mathematical analysis Mechatronics Natural Language Processing (NLP) Neural networks Relational data bases Robotics Simulation and Modeling Tasks Vectors (mathematics)
SummonAdditionalLinks	– databaseName: SpringerLINK Contemporary 1997-Present dbid: RSV link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS8MwEA8yffDF-YnTKRF8UgJd04_kUcThgwzxY-ytpGkyhLmNtfPv965Ntyk60KdSemnCJZe7y13uR8hlCiZyaoRm2nqGBcLELBUIZgbCpazxsriM4Pcf4l5PDAby0d3jzuts9zokWe7UK5fdyjK2Hc5CUOoMXJ5N0HYh4jU8PfcX268flfCOID0hQ_VdhzJ_-sVXZbS0ML8FRUtd023-a5S7ZMeZlvSmWgt7ZMOM90mzhm2gTooPiOqqvKAzlwUHLRxyxJBiEvyQIrjY5J3qkZrnhk4RRqFK7FIjd2mT4uktxUVX1Z-gWBWzfJQ55fkhee3evdzeM4e0wDTIbMEyLjIRpLGOYutnvvVsEFkbchODuQQ7gtRc6NBKFYGAm9CXgbZCZ9rEaWBMJ-NHpDGejM0xoVrx2Dfc052UB9aDJuCUSCUyKSS8yRbxapYn2pUhRzSMUbIsoIwsTICFCbIw6bTI1aLJtKrBsY64Xc9j4sQxR_9GoCUUQvcXi88gSBgdUWMzmSONDHjkgbexhgacOywY6EUtcl3P_0o3vw3q5E_Up2QbzLKgOuhpk0Yxm5szsqU_ird8dl6u9k9Y4_sO priority: 102 providerName: Springer Nature
Title	Fast relational learning using bottom clause propositionalization with artificial neural networks
URI	https://link.springer.com/article/10.1007/s10994-013-5392-1 https://www.proquest.com/docview/1468822259 https://www.proquest.com/docview/1494360772 https://www.proquest.com/docview/1753544306
Volume	94
WOSCitedRecordID	wos000328838500005&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: PRVPQU databaseName: Advanced Technologies & Aerospace Database customDbUrl: eissn: 1573-0565 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002686 issn: 0885-6125 databaseCode: P5Z dateStart: 19970101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 1573-0565 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002686 issn: 0885-6125 databaseCode: K7- dateStart: 19970101 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1573-0565 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002686 issn: 0885-6125 databaseCode: BENPR dateStart: 19970101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database customDbUrl: eissn: 1573-0565 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002686 issn: 0885-6125 databaseCode: M2P dateStart: 19970101 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest – providerCode: PRVAVX databaseName: SpringerLink Journals customDbUrl: eissn: 1573-0565 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002686 issn: 0885-6125 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED-NjQde2PgSHdtkJJ5AFkmcxPYTgmnVJEZVDZgmXiLHsSek0nZNy9_PneO0DIm-7MVVVFuxcp--O98P4E2NLnLtlOXWJ47nykleKwIzQ-Ey3iWNDBn8qws5Gqnraz2OAbc2llX2OjEo6mZmKUb-nq4IkTEr9If5LSfUKMquRgiNB7CXZlkQzM-SrzVxVgakRxSkgpMl77Oa3dW50BQ3FbxAF4Gnd-3Sxtn8Jz8azM5w_74bPoDH0eFkHzsOeQI7bvoU9nswBxZl-xmYoWmXbBFr43BFxJO4YVQaf8MIcmz2i9mJWbWOzQlcoSv3MpN4lZNRTJcRK3ZdKRj1ygw_odK8fQ7fh2ffTs95xF_gFiV5yRuhGpXX0pbSZ03mE5-X3hfCSXSiUE9oK5QtvDYlir0rMp1br2xjnaxz59JGvIDd6WzqXgKzRsjMicSmtch9gkvwqKKNarTS-KQHkPRfv7KxOTlhZEyqTVtlIliFBKuIYFU6gLfrJfOuM8e2yUc9kaoopG21odAAXq__RvGinImZutmK5uhclAmeQbbMwSMftRFMygG869nlr9f8b1OH2zf1Ch6hd5Z38Z4j2F0uVu4YHtrfy5_t4gT2Pp2NxpcngeNx_JKNcRwXP3C8_Hr1B3-QChY
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VUgku9AVioRRXai9FFkmch31AVQWsWnW76qFFFZfgOHaFtOwum10Qf4rfyIyT7FIk9tZDT1EUO3GSb8Zjz-MD2C_QRC6sNNy4wPJY2owXksjMULi0s0GZeQ_-p17W78vra3WxAr_bXBgKq2x1olfU5cjQHvlbShGiySxRR-PvnFijyLvaUmjUsDizv37ikq16d_oB_-9BFHU_Xr4_4Q2rADeIzykvhSxlXGQmzVxURi5wcepcImyGpgGiXxkhTeKUThHMNolUbJw0pbFZEVsblgLv-wAeeuoulJ-L5PNc80epZ5ZEwU04WQ6tF7VO1fNFeEPBEzRJeHh7HlwYt__4Y_00112_bx9oA540BjU7riVgE1bscAvWW7IK1uiubdBdXU3ZpIn9wx4NX8YNo9D_G0aUaqNvzAz0rLJsTOQRdTibHjSpqoz2rBmJWl11g1EtUH_wkfTVU7i6kxd9BqvD0dA-B2a0yCIrAhMWInYBdsGlmNKyVFLhmepA0P7t3DTF14kDZJAvykYTQHIESE4AycMOHM67jOvKI8sa77SgyBslVOULRHRgb34Z1Qf5hPTQjmbURsUiDXCNtaQNLmmpTGKQduBNC8-_HvO_Qb1YPqjX8Ojk8ryX9077Zy_hMVqicb23tQOr08nMvoI182P6tZrseilj8OWuUfsHHzBkGQ
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lj9MwEB4tC0JcWF4rCgsYCS4ga5PYie0DQoilYrWrqgdAKy7BcewVUmlL04L4a_w6ZhKnBSR62wOnKIqdOMk347Hn8QE8qdBErrx23IXEc6m94pUmMjMULht8UqvWg__hVI1G-uzMjHfgZ58LQ2GVvU5sFXU9c7RHfkgpQjSZ5eYwxLCI8dHw5fwrJwYp8rT2dBodRE78j--4fGteHB_hv36aZcM3716_5ZFhgDvE6pLXQtdaVsoVKmR1FpIgixBy4RWaCSgJxgnt8mBsgcD2eWakC9rVzqtKep_WAu97CS4rWRQUTjjOP65ngaxoWSZRiHNOVkTvUe3S9tqCvKngOZonPP1zTtwYun_5Ztspb7j3P3-sG3A9GtrsVScZN2HHT2_BXk9iwaJOuw12aJslW8SYQOwReTTOGaUEnDOiWpt9YW5iV41ncyKV6MLc7CSmsDLay2Ykgl01DkY1QttDG2Hf3IH3F_Ki-7A7nU39XWDOCpV5kbi0EjIk2AWXaMbq2miDZ2YASf_nSxeLshM3yKTclJMmsJQIlpLAUqYDeLbuMu8qkmxrfNADpIzKqSk36BjA4_VlVCvkK7JTP1tRGyNFkeDaa0sbXOpS-cSkGMDzHqq_PeZfg7q3fVCP4CqCtTw9Hp3ch2tooMpuy-sAdpeLlX8AV9y35edm8bAVOAafLhq0vwDu82za
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=Fast+relational+learning+using+bottom+clause+propositionalization+with+artificial+neural+networks&rft.jtitle=Machine+learning&rft.au=Franca%2C+Manoel+VM&rft.au=Zaverucha%2C+Gerson&rft.au=d%27Avila+Garcez%2C+Artur+S&rft.date=2014-01-01&rft.issn=0885-6125&rft.eissn=1573-0565&rft.volume=94&rft.issue=1&rft.spage=81&rft.epage=104&rft_id=info:doi/10.1007%2Fs10994-013-5392-1&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0885-6125&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0885-6125&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0885-6125&client=summon