αILP: thinking visual scenes as differentiable logic programs

Deep neural learning has shown remarkable performance at learning representations for visual object categorization. However, deep neural networks such as CNNs do not explicitly encode objects and relations among them. This limits their success on tasks that require a deep logical understanding of vi...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Machine learning Ročník 112; číslo 5; s. 1465 - 1497
Hlavní autoři: Shindo, Hikaru, Pfanschilling, Viktor, Dhami, Devendra Singh, Kersting, Kristian
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.05.2023
Springer Nature B.V
Témata:
ISSN:0885-6125, 1573-0565
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Deep neural learning has shown remarkable performance at learning representations for visual object categorization. However, deep neural networks such as CNNs do not explicitly encode objects and relations among them. This limits their success on tasks that require a deep logical understanding of visual scenes, such as Kandinsky patterns and Bongard problems. To overcome these limitations, we introduce α ILP , a novel differentiable inductive logic programming framework that learns to represent scenes as logic programs—intuitively, logical atoms correspond to objects, attributes, and relations, and clauses encode high-level scene information. α ILP has an end-to-end reasoning architecture from visual inputs. Using it, α ILP performs differentiable inductive logic programming on complex visual scenes, i.e., the logical rules are learned by gradient descent. Our extensive experiments on Kandinsky patterns and CLEVR-Hans benchmarks demonstrate the accuracy and efficiency of α ILP in learning complex visual-logical concepts.
AbstractList Deep neural learning has shown remarkable performance at learning representations for visual object categorization. However, deep neural networks such as CNNs do not explicitly encode objects and relations among them. This limits their success on tasks that require a deep logical understanding of visual scenes, such as Kandinsky patterns and Bongard problems. To overcome these limitations, we introduce α ILP , a novel differentiable inductive logic programming framework that learns to represent scenes as logic programs—intuitively, logical atoms correspond to objects, attributes, and relations, and clauses encode high-level scene information. α ILP has an end-to-end reasoning architecture from visual inputs. Using it, α ILP performs differentiable inductive logic programming on complex visual scenes, i.e., the logical rules are learned by gradient descent. Our extensive experiments on Kandinsky patterns and CLEVR-Hans benchmarks demonstrate the accuracy and efficiency of α ILP in learning complex visual-logical concepts.
Deep neural learning has shown remarkable performance at learning representations for visual object categorization. However, deep neural networks such as CNNs do not explicitly encode objects and relations among them. This limits their success on tasks that require a deep logical understanding of visual scenes, such as Kandinsky patterns and Bongard problems. To overcome these limitations, we introduce $$\alpha {\textit{ILP}}$$ α ILP , a novel differentiable inductive logic programming framework that learns to represent scenes as logic programs—intuitively, logical atoms correspond to objects, attributes, and relations, and clauses encode high-level scene information. $$\alpha$$ α ILP has an end-to-end reasoning architecture from visual inputs. Using it, $$\alpha$$ α ILP performs differentiable inductive logic programming on complex visual scenes, i.e., the logical rules are learned by gradient descent. Our extensive experiments on Kandinsky patterns and CLEVR-Hans benchmarks demonstrate the accuracy and efficiency of $$\alpha {\textit{ILP}}$$ α ILP in learning complex visual-logical concepts.
Deep neural learning has shown remarkable performance at learning representations for visual object categorization. However, deep neural networks such as CNNs do not explicitly encode objects and relations among them. This limits their success on tasks that require a deep logical understanding of visual scenes, such as Kandinsky patterns and Bongard problems. To overcome these limitations, we introduce αILP, a novel differentiable inductive logic programming framework that learns to represent scenes as logic programs—intuitively, logical atoms correspond to objects, attributes, and relations, and clauses encode high-level scene information. αILP has an end-to-end reasoning architecture from visual inputs. Using it, αILP performs differentiable inductive logic programming on complex visual scenes, i.e., the logical rules are learned by gradient descent. Our extensive experiments on Kandinsky patterns and CLEVR-Hans benchmarks demonstrate the accuracy and efficiency of αILP in learning complex visual-logical concepts.
Author Kersting, Kristian
Shindo, Hikaru
Dhami, Devendra Singh
Pfanschilling, Viktor
Author_xml – sequence: 1
  givenname: Hikaru
  surname: Shindo
  fullname: Shindo, Hikaru
  email: hikaru.shindo@cs.tu-darmstadt.de
  organization: TU Darmstadt
– sequence: 2
  givenname: Viktor
  surname: Pfanschilling
  fullname: Pfanschilling, Viktor
  organization: TU Darmstadt
– sequence: 3
  givenname: Devendra Singh
  surname: Dhami
  fullname: Dhami, Devendra Singh
  organization: TU Darmstadt, Hessian Center for AI (hessian.AI)
– sequence: 4
  givenname: Kristian
  surname: Kersting
  fullname: Kersting, Kristian
  organization: TU Darmstadt, Hessian Center for AI (hessian.AI), Centre for Cognitive Science, TU Darmstadt
BookMark eNp9kM1KAzEUhYNUsK2-gKsB16M3mUwmcSFI8adQ0IWuQyaTjKnTTE2mgo_li_hMplYQXHR1uXC-e849EzTyvTcInWI4xwDVRcQgBM2BFDmwgkCOD9AYl1VaS1aO0Bg4L3OGSXmEJjEuAYAwzsbo6utzvni8zIYX51-db7N3Fzeqy6I23sRMxaxx1ppg_OBU3Zms61uns3Xo26BW8RgdWtVFc_I7p-j59uZpdp8vHu7ms-tFrknFcc6xFZwKDZYwI2xNFLY1TZkKxWvLS10DrRk3uGCKikY3VcmZUFVDDbVgRTFFZ7u7yfhtY-Igl_0m-GQpCU-vM8oYTiqyU-nQxxiMlevgVip8SAxy25Pc9SRTT_KnJ7mF-D9Iu0ENrvdDUK7bjxY7NCYf35rwl2oP9Q11LH6H
CitedBy_id crossref_primary_10_1007_s10994_025_06798_x
crossref_primary_10_1007_s10994_024_06610_2
crossref_primary_10_1177_02783649251353181
crossref_primary_10_1007_s10994_025_06780_7
crossref_primary_10_1016_j_knosys_2025_113906
crossref_primary_10_1016_j_artint_2023_104062
crossref_primary_10_3390_math13111707
Cites_doi 10.24963/ijcai.2017/371
10.1016/j.artint.2021.103602
10.1007/BF03037089
10.1609/aaai.v35i6.16637
10.1007/978-3-319-78090-0_10
10.1016/j.artint.2015.08.011
10.1007/BF00117105
10.24963/ijcai.2020/243
10.1007/978-3-642-96826-6
10.1609/aimag.v43i1.19122
10.24963/ijcai.2020/688
10.1098/rsfs.2018.0011
10.1016/j.artint.2021.103649
10.1007/3-540-62927-0
10.1016/j.artint.2021.103504
10.1007/s10994-021-06089-1
10.1016/j.artint.2021.103546
10.1109/ICCV.2017.322
10.1007/978-3-540-78652-8
10.1007/BF03037227
10.1109/CVPR46437.2021.00362
10.1007/978-3-030-29726-8_1
10.1145/35043.35046
10.7551/mitpress/1192.001.0001
10.1109/CVPR.2016.91
10.1609/aaai.v32i1.11806
10.1609/aaai.v35i18.17931
10.1007/s10994-019-05862-7
10.3233/FAIA210359
10.1109/CVPR.2016.90
10.1109/ICCV.2015.279
10.1613/jair.5714
10.24963/ijcai.2017/221
10.1007/978-3-319-11558-0_22
10.1007/s10994-018-5750-0
10.1017/S1471068413000689
10.1007/s10994-020-05934-z
10.1613/jair.1.11203
10.1109/CVPR.2017.215
10.1609/aaai.v36i8.20795
10.24963/ijcai.2019/847
10.1007/978-3-031-01574-8
10.1007/978-3-540-78469-2_23
10.1609/aaai.v35i6.16639
ContentType Journal Article
Copyright The Author(s) 2023
The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s) 2023
– notice: The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID C6C
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/s10994-023-06320-1
DatabaseName Springer Nature OA Free Journals
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 Edition)
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
Advanced Technologies & Aerospace Database
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
CrossRef
Computer Science Database
Database_xml – sequence: 1
  dbid: BENPR
  name: ProQuest Central Database Suite (ProQuest)
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1573-0565
EndPage 1497
ExternalDocumentID 10_1007_s10994_023_06320_1
GrantInformation_xml – fundername: Technische Universität Darmstadt (3139)
– fundername: TAILOR
  grantid: 952215
– fundername: SPAICER
  grantid: 01MK20015E
– fundername: AICO
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
C6C
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
ID FETCH-LOGICAL-c2781-81f9849c0f26e9fb2a1fb40883a8bf85cb04b68e136a49dcd75869a7d4e4f0f93
IEDL.DBID RSV
ISSN 0885-6125
IngestDate Wed Nov 05 00:48:50 EST 2025
Sat Nov 29 01:43:29 EST 2025
Tue Nov 18 22:24:58 EST 2025
Fri Feb 21 02:45:46 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 5
Keywords Object-centric learning
Neuro-symbolic AI
Inductive logic programming
Differentiable reasoning
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2781-81f9849c0f26e9fb2a1fb40883a8bf85cb04b68e136a49dcd75869a7d4e4f0f93
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
OpenAccessLink https://link.springer.com/10.1007/s10994-023-06320-1
PQID 2809964661
PQPubID 54194
PageCount 33
ParticipantIDs proquest_journals_2809964661
crossref_primary_10_1007_s10994_023_06320_1
crossref_citationtrail_10_1007_s10994_023_06320_1
springer_journals_10_1007_s10994_023_06320_1
PublicationCentury 2000
PublicationDate 20230500
2023-05-00
20230501
PublicationDateYYYYMMDD 2023-05-01
PublicationDate_xml – month: 5
  year: 2023
  text: 20230500
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
– name: Dordrecht
PublicationTitle Machine learning
PublicationTitleAbbrev Mach Learn
PublicationYear 2023
Publisher Springer US
Springer Nature B.V
Publisher_xml – name: Springer US
– name: Springer Nature B.V
References Sourek, G., Svatos, M., Zelezný, F., Schockaert, S., & Kuzelka, O. (2017). Stacked structure learning for lifted relational neural networks. In N. Lachiche, C. Vrain (Eds.), Proceedings of the 27th international conference on inductive logic programming. Lecture notes in computer science (Vol. 10759, pp. 140–151).
Holzinger, A., Saranti, A., & Müller, H. (2021). Kandinsky patterns: An experimental exploration environment for pattern analysis and machine intelligence. In CoRRarXiv:2103.00519.
KautzHThe third AI summer: AAAI Robert S. Engelmore memorial lectureAI Magazine20224319310410.1609/aimag.v43i1.19122
Goyal, K., Neubig, G., Dyer, C., & Berg-Kirkpatrick, T. (2018). A continuous relaxation of beam search for end-to-end training of neural sequence models. In Proceedings of the 32th AAAI conference on artificial intelligence (AAAI) (Vol. 32, No 1).
Lloyd, J. W. (1984). Foundations of logic programming.
Dai, W.-Z., Xu, Q., Yu, Y., & Zhou, Z.-H. (2019). Bridging machine learning and logical reasoning by abductive learning. In Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 32).
LocatelloFWeissenbornDUnterthinerTMahendranAHeigoldGUszkoreitJDosovitskiyAKipfTObject-centric learning with slot attentionProceedings of the Advances in Neural Information Processing Systems (NeurIPS)2020331152511538
Santoro, A., Faulkner, R., Raposo, D., Rae, J., Chrzanowski, M., Weber, T., Wierstra, D., Vinyals, O., Pascanu, R., & Lillicrap, T. (2018). Relational recurrent neural networks. In: Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 31).
Holzinger, A., Kickmeier-Rust, M., & Müller, H. (2019). Kandinsky patterns as IQ-test for machine learning. In Proceedings of the 3rd international cross-domain conference for machine learning and knowledge extraction (CD-MAKE) (pp. 1–14).
Manhaeve, R., Dumancic, S., Kimmig, A., Demeester, T., & De Raedt, L. (2018). Deepproblog: Neural probabilistic logic programming. In Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 31).
Vedantam, R., Szlam, A., Nickel, M., Morcos, A., & Lake, B. M. (2021). Curi: A benchmark for productive concept learning under uncertainty. In Proceedings of the 38th international conference on machine learning (ICML) (Vol. 139, pp. 10519–10529).
Pietruszka, M., Borchmann, L., & Gralinski, F. (2021). Successive halving top-k operator. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI) (Vol. 35, No. 18, pp. 15869–15870).
QuinlanJRLearning logical definitions from relationsMachine Learning1990523926610.1007/BF00117105
KowalskiRAThe early years of logic programmingCommunications of the ACM1988311384384141510.1145/35043.35046
Redmon, J., Divvala, S. K., Girshick, R. B., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 779–788).
Cropper, A., & Muggleton, S. H. (2016). Metagol system. https://github.com/metagol/metagol.
Lee, J., Lee, Y., Kim, J., Kosiorek, A., Choi, S., & Teh, Y. W. (2019). Set transformer: A framework for attention-based permutation-invariant neural networks. In Proceedings of the 36th international conference on machine learning (ICML) (Vol. 97, pp. 3744–3753).
Raedt, L. d., Dumančić, S., Manhaeve, R., & Marra, G. (2020). From statistical relational to neuro-symbolic artificial intelligence. In Proceedings of the 29th international joint conference on artificial intelligence (IJCAI) (pp. 4943–4950).
CropperAMorelRMuggletonSLearning higher-order logic programsMachine Learning201910912891322412506010.1007/s10994-019-05862-707255749
Cuturi, M., & Blondel, M. (2017). Soft-DTW: A differentiable loss function for time-series. In Proceedings of the 34th international conference on machine learning (ICML) (Vol. 70, pp. 894–903).
Ray, O., & Inoue, K. (2007). Mode-directed inverse entailment for full clausal theories. In Proceedings of the 17th international conference on inductive logic programming (ILP). Lecture notes in computer science (Vol. 4894, pp. 225–238).
Stammer, W., Schramowski, P., & Kersting, K. (2021). Right for the right concept: Revising neuro-symbolic concepts by interacting with their explanations. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3619–3629).
He, K., Gkioxari, G., Dollár, P., & Girshick, R. B. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 2980–2988).
RussellSNorvigPArtificial intelligence: A modern approach20093Hoboken, NJPrentice Hall Press0835.68093
BongardMMHawkinsJKPattern recognition1970New YorkSpartan Books0205.21201
Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C. L., & Girshick, R. B. (2017). Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1988–1997).
KimJRicciMSerreTNot-So-CLEVR: Learning same-different relations strains feedforward neural networksInterface Focus201882018001110.1098/rsfs.2018.0011
Nguembang FadjaARiguzziFLifted discriminative learning of probabilistic logic programsMachine Learning2019108711111135395999310.1007/s10994-018-5750-01493.68310
De Raedt, L., Frasconi, P., Kersting, K., & Muggleton, S. H. (Eds.) (2008). Probabilistic inductive logic programming—theory and applications. Lecture Notes in Computer Science (Vol. 4911). Berlin: Springer.
ManhaeveRDumančićSKimmigADemeesterTDe RaedtLNeural probabilistic logic programming in DeepProbLogArtificial Intelligence2021298103504424460810.1016/j.artint.2021.10350407418672
Rocktäschel, T., & Riedel, S. (2017). End-to-end differentiable proving. In Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 30).
Ruder, S. (2016). An overview of gradient descent optimization algorithms. In CoRRarXiv:1609.04747.
Tsamoura, E., Hospedales, T. M., & Michael, L. (2021). Neural-symbolic integration: A compositional perspective. In Proceedings of the 35th AAAI conference on artificial intelligence (AAAI) (pp. 5051–5060).
Jiang, Z., & Luo, S. (2019). Neural logic reinforcement learning. In Proceedings of the 36th international conference on machine learning (ICML) (Vol. 97, pp. 3110–3119).
Law, M., Russo, A., & Broda, K. (2014). Inductive learning of answer set programs. In E. Fermé, J. Leite (Eds.), Logics in artificial intelligence—14th European Conference (JELIA). Lecture Notes in Computer Science (Vol. 8761, pp. 311–325).
Donadello, I., Serafini, L., & d’Avila Garcez, A. (2017). Logic tensor networks for semantic image interpretation. In Proceedings of the 26th international joint conference on artificial intelligence (IJCAI) (pp. 1596–1602).
Sen, P., Carvalho, B. W. S. R. D., Riegel, R., & Gray, A. (2022). Neuro-symbolic inductive logic programming with logical neural networks. In Proceedings of the AAAI conference on artificial intelligence (AAAI) (Vol. 36, No 8, pp. 8212–8219).
Shindo, H., Nishino, M., & Yamamoto, A. (2021). Differentiable inductive logic programming for structured examples. In Proceedings of the 35th AAAI conference on artificial intelligence (AAAI) (pp. 5034–5041).
Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015). Vqa: Visual question answering. In Proceedings of the IEEE international conference on computer vision (ICCV).
van KriekenEAcarEvan HarmelenFAnalyzing differentiable fuzzy logic operatorsArtificial Intelligence2022302103602432734410.1016/j.artint.2021.1036021490.68233
Bošnjak, M., Rocktäschel, T., Naradowsky, J., & Riedel, S. (2017). Programming with a differentiable forth interpreter. In Proceedings of the 34th international conference on machine learning (ICML) (Vol. 70, pp. 547–556).
CropperAMorelRLearning programs by learning from failuresMachine Learning20211104801856425808210.1007/s10994-020-05934-z07432822
Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 28).
Mensch, A., & Blondel, M. (2018). Differentiable dynamic programming for structured prediction and attention. In Proceedings of the 35th international conference on machine learning (ICML) (Vol. 80, pp. 3462–3471).
MüllerHHolzingerAKandinsky patternsArtificial Intelligence2021300103546427559810.1016/j.artint.2021.10354607418690
De Raedt, L., Kersting, K., Natarajan, S., & Poole, D. (2016). Statistical relational artificial intelligence: Logic, probability, and computation. In Synthesis lectures on artificial intelligence and machine learning (Vol. 32). San Rafael, CA: Morgan & Claypool.
Mao, J., Gan, C., Kohli, P., Tenenbaum, J. B., & Wu, J. (2019). The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision. In Proceedings of the 7th international conference on learning representations (ICLR).
BadreddineSd’Avila GarcezASerafiniLSprangerMLogic tensor networksArtificial Intelligence2022303103649435321810.1016/j.artint.2021.10364907482899
CropperADumancicSEvansRMuggletonSHInductive logic programming at 30Machine Learning20221111147172437584810.1007/s10994-021-06089-107510309
ShapiroEYAlgorithmic program debugging1983CambridgeMIT Press0589.68003
Dittadi, A., Papa, S., De Vita, M., Schölkopf, B., Winther, O., & Locatello, F. (2022). Generalization and robustness implications in object-centric learning. In Proceedings of the 39th international conference on machine learning (ICML).
MuggletonSInverse Entailment and ProgolNew Generation Computing, Special issue on Inductive Logic Programming1995133–424528610.1007/BF03037227
Burgess, C. P., Matthey, L., Watters, N., Kabra, R., Higgins, I., Botvinick, M. M., & Lerchner, A. (2019). Monet: Unsupervised scene decomposition and representation. CoRR arXiv:1901.11390.
Plotkin, G. (1971). A further note on inductive
F Locatello (6320_CR37) 2020; 33
6320_CR70
MM Bongard (6320_CR6) 1970
EY Shapiro (6320_CR63) 1983
6320_CR72
H Kautz (6320_CR30) 2022; 43
6320_CR35
6320_CR34
6320_CR36
6320_CR74
E Bellodi (6320_CR4) 2015; 15
6320_CR32
W Nie (6320_CR48) 2020; 33
6320_CR38
6320_CR1
6320_CR2
6320_CR5
6320_CR7
6320_CR8
6320_CR9
6320_CR40
J Kim (6320_CR31) 2018; 8
SH Muggleton (6320_CR43) 1991; 8
JR Quinlan (6320_CR52) 1990; 5
S Russell (6320_CR60) 2009
6320_CR47
6320_CR42
6320_CR41
RA Kowalski (6320_CR33) 1988; 31
F Petersen (6320_CR49) 2021; 34
S Muggleton (6320_CR44) 1995; 13
A Cropper (6320_CR11) 2021; 110
R Evans (6320_CR22) 2018; 61
A Cropper (6320_CR12) 2019; 109
6320_CR51
6320_CR50
6320_CR13
6320_CR57
6320_CR56
6320_CR15
6320_CR59
6320_CR14
6320_CR58
6320_CR53
6320_CR55
6320_CR54
6320_CR17
6320_CR16
6320_CR19
G Sourek (6320_CR68) 2018; 62
A Nguembang Fadja (6320_CR46) 2019; 108
H Müller (6320_CR45) 2021; 300
6320_CR62
6320_CR61
Y Xie (6320_CR73) 2020; 33
M Diligenti (6320_CR18) 2017; 244
6320_CR24
R Manhaeve (6320_CR39) 2021; 298
6320_CR23
6320_CR67
6320_CR26
6320_CR25
6320_CR69
6320_CR20
6320_CR64
S Badreddine (6320_CR3) 2022; 303
6320_CR66
6320_CR21
6320_CR65
E van Krieken (6320_CR71) 2022; 302
A Cropper (6320_CR10) 2022; 111
6320_CR28
6320_CR27
6320_CR29
References_xml – reference: Burgess, C. P., Matthey, L., Watters, N., Kabra, R., Higgins, I., Botvinick, M. M., & Lerchner, A. (2019). Monet: Unsupervised scene decomposition and representation. CoRR arXiv:1901.11390.
– reference: Goyal, K., Neubig, G., Dyer, C., & Berg-Kirkpatrick, T. (2018). A continuous relaxation of beam search for end-to-end training of neural sequence models. In Proceedings of the 32th AAAI conference on artificial intelligence (AAAI) (Vol. 32, No 1).
– reference: XieYDaiHChenMDaiBZhaoTZhaHWeiWPfisterTDifferentiable top-k with optimal transportProceedings of the Advances in Neural Information Processing Systems (NeurIPS)2020332052020531
– reference: CropperAMorelRMuggletonSLearning higher-order logic programsMachine Learning201910912891322412506010.1007/s10994-019-05862-707255749
– reference: CropperADumancicSEvansRMuggletonSHInductive logic programming at 30Machine Learning20221111147172437584810.1007/s10994-021-06089-107510309
– reference: Stammer, W., Schramowski, P., & Kersting, K. (2021). Right for the right concept: Revising neuro-symbolic concepts by interacting with their explanations. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 3619–3629).
– reference: BellodiERiguzziFStructure learning of probabilistic logic programs by searching the clause spaceTheory and Practice of Logic Programming201515216921210.1017/S14710684130006891379.68269
– reference: De Raedt, L., Kersting, K., Natarajan, S., & Poole, D. (2016). Statistical relational artificial intelligence: Logic, probability, and computation. In Synthesis lectures on artificial intelligence and machine learning (Vol. 32). San Rafael, CA: Morgan & Claypool.
– reference: MuggletonSInverse Entailment and ProgolNew Generation Computing, Special issue on Inductive Logic Programming1995133–424528610.1007/BF03037227
– reference: Sourek, G., Svatos, M., Zelezný, F., Schockaert, S., & Kuzelka, O. (2017). Stacked structure learning for lifted relational neural networks. In N. Lachiche, C. Vrain (Eds.), Proceedings of the 27th international conference on inductive logic programming. Lecture notes in computer science (Vol. 10759, pp. 140–151).
– reference: d’Avila Garcez, A., & Lamb, L. C. (2020). Neurosymbolic AI: The 3rd wave. In CoRRarXiv:2012.05876.
– reference: Raedt, L. d., Dumančić, S., Manhaeve, R., & Marra, G. (2020). From statistical relational to neuro-symbolic artificial intelligence. In Proceedings of the 29th international joint conference on artificial intelligence (IJCAI) (pp. 4943–4950).
– reference: Rocktäschel, T., & Riedel, S. (2017). End-to-end differentiable proving. In Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 30).
– reference: Holzinger, A., Saranti, A., & Müller, H. (2021). Kandinsky patterns: An experimental exploration environment for pattern analysis and machine intelligence. In CoRRarXiv:2103.00519.
– reference: BadreddineSd’Avila GarcezASerafiniLSprangerMLogic tensor networksArtificial Intelligence2022303103649435321810.1016/j.artint.2021.10364907482899
– reference: Law, M., Russo, A., & Broda, K. (2014). Inductive learning of answer set programs. In E. Fermé, J. Leite (Eds.), Logics in artificial intelligence—14th European Conference (JELIA). Lecture Notes in Computer Science (Vol. 8761, pp. 311–325).
– reference: Ray, O., & Inoue, K. (2007). Mode-directed inverse entailment for full clausal theories. In Proceedings of the 17th international conference on inductive logic programming (ILP). Lecture notes in computer science (Vol. 4894, pp. 225–238).
– reference: He, K., Gkioxari, G., Dollár, P., & Girshick, R. B. (2017). Mask r-cnn. In Proceedings of the IEEE international conference on computer vision (ICCV) (pp. 2980–2988).
– reference: SourekGAschenbrennerVZeleznýFSchockaertSKuzelkaOLifted relational neural networks: Efficient learning of latent relational structuresJournal of Artificial Intelligence Research20186269100381750110.1613/jair.1.112031444.68163
– reference: Sen, P., Carvalho, B. W. S. R. D., Riegel, R., & Gray, A. (2022). Neuro-symbolic inductive logic programming with logical neural networks. In Proceedings of the AAAI conference on artificial intelligence (AAAI) (Vol. 36, No 8, pp. 8212–8219).
– reference: LocatelloFWeissenbornDUnterthinerTMahendranAHeigoldGUszkoreitJDosovitskiyAKipfTObject-centric learning with slot attentionProceedings of the Advances in Neural Information Processing Systems (NeurIPS)2020331152511538
– reference: Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the 3rd international conference on learning representation (ICLR).
– reference: Lee, J., Lee, Y., Kim, J., Kosiorek, A., Choi, S., & Teh, Y. W. (2019). Set transformer: A framework for attention-based permutation-invariant neural networks. In Proceedings of the 36th international conference on machine learning (ICML) (Vol. 97, pp. 3744–3753).
– reference: Ross, A. S., Hughes, M. C., & Doshi-Velez, F. (2017). Right for the right reasons: Training differentiable models by constraining their explanations. In Proceedings of the 26 international joint conference on artificial intelligence (IJCAI) (pp. 2662–2670).
– reference: MüllerHHolzingerAKandinsky patternsArtificial Intelligence2021300103546427559810.1016/j.artint.2021.10354607418690
– reference: CropperAMorelRLearning programs by learning from failuresMachine Learning20211104801856425808210.1007/s10994-020-05934-z07432822
– reference: Holzinger, A., Kickmeier-Rust, M., & Müller, H. (2019). Kandinsky patterns as IQ-test for machine learning. In Proceedings of the 3rd international cross-domain conference for machine learning and knowledge extraction (CD-MAKE) (pp. 1–14).
– reference: KimJRicciMSerreTNot-So-CLEVR: Learning same-different relations strains feedforward neural networksInterface Focus201882018001110.1098/rsfs.2018.0011
– reference: KautzHThe third AI summer: AAAI Robert S. Engelmore memorial lectureAI Magazine20224319310410.1609/aimag.v43i1.19122
– reference: QuinlanJRLearning logical definitions from relationsMachine Learning1990523926610.1007/BF00117105
– reference: Mao, J., Gan, C., Kohli, P., Tenenbaum, J. B., & Wu, J. (2019). The neuro-symbolic concept learner: Interpreting scenes, words, and sentences from natural supervision. In Proceedings of the 7th international conference on learning representations (ICLR).
– reference: KowalskiRAThe early years of logic programmingCommunications of the ACM1988311384384141510.1145/35043.35046
– reference: Lloyd, J. W. (1984). Foundations of logic programming.
– reference: Yang, Z., Ishay, A., & Lee, J. (2020). Neurasp: Embracing neural networks into answer set programming. In Proceedings of the 29th international joint conference on artificial intelligence (IJCAI) (pp. 1755–1762).
– reference: DiligentiMGoriMSaccàCSemantic-based regularization for learning and inferenceArtificial Intelligence2017244143165360599510.1016/j.artint.2015.08.0111404.68100
– reference: Vedantam, R., Szlam, A., Nickel, M., Morcos, A., & Lake, B. M. (2021). Curi: A benchmark for productive concept learning under uncertainty. In Proceedings of the 38th international conference on machine learning (ICML) (Vol. 139, pp. 10519–10529).
– reference: Tsamoura, E., Hospedales, T. M., & Michael, L. (2021). Neural-symbolic integration: A compositional perspective. In Proceedings of the 35th AAAI conference on artificial intelligence (AAAI) (pp. 5051–5060).
– reference: Pietruszka, M., Borchmann, L., & Gralinski, F. (2021). Successive halving top-k operator. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI) (Vol. 35, No. 18, pp. 15869–15870).
– reference: ManhaeveRDumančićSKimmigADemeesterTDe RaedtLNeural probabilistic logic programming in DeepProbLogArtificial Intelligence2021298103504424460810.1016/j.artint.2021.10350407418672
– reference: RussellSNorvigPArtificial intelligence: A modern approach20093Hoboken, NJPrentice Hall Press0835.68093
– reference: Ruder, S. (2016). An overview of gradient descent optimization algorithms. In CoRRarXiv:1609.04747.
– reference: Cuturi, M., & Blondel, M. (2017). Soft-DTW: A differentiable loss function for time-series. In Proceedings of the 34th international conference on machine learning (ICML) (Vol. 70, pp. 894–903).
– reference: Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015). Vqa: Visual question answering. In Proceedings of the IEEE international conference on computer vision (ICCV).
– reference: Dai, W.-Z., Xu, Q., Yu, Y., & Zhou, Z.-H. (2019). Bridging machine learning and logical reasoning by abductive learning. In Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 32).
– reference: van KriekenEAcarEvan HarmelenFAnalyzing differentiable fuzzy logic operatorsArtificial Intelligence2022302103602432734410.1016/j.artint.2021.1036021490.68233
– reference: BongardMMHawkinsJKPattern recognition1970New YorkSpartan Books0205.21201
– reference: NieWYuZMaoLPatelABZhuYAnandkumarABongard-logo: A new benchmark for human-level concept learning and reasoningProceedings of the Advances in Neural Information Processing Systems (NeurIPS)2020331646816480
– reference: Si, X., Raghothaman, M., Heo, K., & Naik, M. (2019). Synthesizing datalog programs using numerical relaxation. In Proceedings of the 28th international joint conference on artificial intelligence (IJCAI) (pp. 6117–6124).
– reference: Solar-Lezama, A. (2008). Program synthesis by sketching. Ph.D. Thesis.
– reference: Donadello, I., Serafini, L., & d’Avila Garcez, A. (2017). Logic tensor networks for semantic image interpretation. In Proceedings of the 26th international joint conference on artificial intelligence (IJCAI) (pp. 1596–1602).
– reference: Johnson, J., Hariharan, B., van der Maaten, L., Fei-Fei, L., Zitnick, C. L., & Girshick, R. B. (2017). Clevr: A diagnostic dataset for compositional language and elementary visual reasoning. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 1988–1997).
– reference: Shindo, H., Nishino, M., & Yamamoto, A. (2021). Differentiable inductive logic programming for structured examples. In Proceedings of the 35th AAAI conference on artificial intelligence (AAAI) (pp. 5034–5041).
– reference: MuggletonSHInductive logic programmingNew Generation Computing19918429531810.1007/BF030370890712.68022
– reference: Nienhuys-Cheng, S.-H., Wolf, R. D., Siekmann, J., & Carbonell, J. G. (1997). Foundations of inductive logic programming.
– reference: He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770–778).
– reference: EvansRGrefenstetteELearning explanatory rules from noisy dataJournal of Artificial Intelligence Research201861164376619810.1613/jair.57141426.68235
– reference: Jiang, Z., & Luo, S. (2019). Neural logic reinforcement learning. In Proceedings of the 36th international conference on machine learning (ICML) (Vol. 97, pp. 3110–3119).
– reference: Nguembang FadjaARiguzziFLifted discriminative learning of probabilistic logic programsMachine Learning2019108711111135395999310.1007/s10994-018-5750-01493.68310
– reference: Cropper, A., & Muggleton, S. H. (2016). Metagol system. https://github.com/metagol/metagol.
– reference: Dittadi, A., Papa, S., De Vita, M., Schölkopf, B., Winther, O., & Locatello, F. (2022). Generalization and robustness implications in object-centric learning. In Proceedings of the 39th international conference on machine learning (ICML).
– reference: PetersenFBorgeltCKuehneHDeussenOLearning with algorithmic supervision via continuous relaxationsProceedings of the Advances in Neural Information Processing Systems (NeurIPS)2021341652016531
– reference: Redmon, J., Divvala, S. K., Girshick, R. B., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (pp. 779–788).
– reference: Bošnjak, M., Rocktäschel, T., Naradowsky, J., & Riedel, S. (2017). Programming with a differentiable forth interpreter. In Proceedings of the 34th international conference on machine learning (ICML) (Vol. 70, pp. 547–556).
– reference: Engelcke, M., Kosiorek, A. R., Jones, O. P., & Posner, I. (2020). Genesis: Generative scene inference and sampling with object-centric latent representations. In Proceedings of the 8th international conference on learning representations (ICLR).
– reference: Minervini, P., Riedel, S., Stenetorp, P., Grefenstette, E., & Rocktäschel, T. (2020). Learning reasoning strategies in end-to-end differentiable proving. In Proceedings of the 37th international conference on machine learning (ICML).
– reference: Manhaeve, R., Dumancic, S., Kimmig, A., Demeester, T., & De Raedt, L. (2018). Deepproblog: Neural probabilistic logic programming. In Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 31).
– reference: Amizadeh, S., Palangi, H., Polozov, A., Huang, Y., & Koishida, K. (2020). Neuro-symbolic visual reasoning: Disentangling visual from reasoning. Proceedings of the 37th international conference on machine learning (ICML) (Vol. 119, pp. 279–290).
– reference: Plotkin, G. (1971). A further note on inductive generalization. In Machine intelligence (Vol. 6).
– reference: Mensch, A., & Blondel, M. (2018). Differentiable dynamic programming for structured prediction and attention. In Proceedings of the 35th international conference on machine learning (ICML) (Vol. 80, pp. 3462–3471).
– reference: Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 28).
– reference: Santoro, A., Faulkner, R., Raposo, D., Rae, J., Chrzanowski, M., Weber, T., Wierstra, D., Vinyals, O., Pascanu, R., & Lillicrap, T. (2018). Relational recurrent neural networks. In: Proceedings of the advances in neural information processing systems (NeurIPS) (Vol. 31).
– reference: Besold, T. R., d’Avila Garcez, A. S., Bader, S., Bowman, H., Domingos, P. M., Hitzler, P., Kühnberger, K., Lamb, L. C., Lowd, D., Lima, P. M. V., de Penning, L., Pinkas, G., Poon, H., & Zaverucha, G. (2017). Neural-symbolic learning and reasoning: A survey and interpretation. In CoRRarXiv:1711.03902.
– reference: De Raedt, L., Frasconi, P., Kersting, K., & Muggleton, S. H. (Eds.) (2008). Probabilistic inductive logic programming—theory and applications. Lecture Notes in Computer Science (Vol. 4911). Berlin: Springer.
– reference: ShapiroEYAlgorithmic program debugging1983CambridgeMIT Press0589.68003
– ident: 6320_CR58
  doi: 10.24963/ijcai.2017/371
– volume: 302
  start-page: 103602
  year: 2022
  ident: 6320_CR71
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2021.103602
– volume: 8
  start-page: 295
  issue: 4
  year: 1991
  ident: 6320_CR43
  publication-title: New Generation Computing
  doi: 10.1007/BF03037089
– ident: 6320_CR64
  doi: 10.1609/aaai.v35i6.16637
– ident: 6320_CR40
– volume-title: Pattern recognition
  year: 1970
  ident: 6320_CR6
– ident: 6320_CR67
  doi: 10.1007/978-3-319-78090-0_10
– ident: 6320_CR28
– volume: 244
  start-page: 143
  year: 2017
  ident: 6320_CR18
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2015.08.011
– ident: 6320_CR21
– volume: 5
  start-page: 239
  year: 1990
  ident: 6320_CR52
  publication-title: Machine Learning
  doi: 10.1007/BF00117105
– ident: 6320_CR74
  doi: 10.24963/ijcai.2020/243
– ident: 6320_CR36
  doi: 10.1007/978-3-642-96826-6
– volume: 33
  start-page: 20520
  year: 2020
  ident: 6320_CR73
  publication-title: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)
– ident: 6320_CR14
– volume: 43
  start-page: 93
  issue: 1
  year: 2022
  ident: 6320_CR30
  publication-title: AI Magazine
  doi: 10.1609/aimag.v43i1.19122
– ident: 6320_CR53
  doi: 10.24963/ijcai.2020/688
– volume: 8
  start-page: 20180011
  year: 2018
  ident: 6320_CR31
  publication-title: Interface Focus
  doi: 10.1098/rsfs.2018.0011
– ident: 6320_CR35
– volume: 303
  start-page: 103649
  year: 2022
  ident: 6320_CR3
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2021.103649
– ident: 6320_CR47
  doi: 10.1007/3-540-62927-0
– ident: 6320_CR7
– ident: 6320_CR41
– ident: 6320_CR66
– volume: 298
  start-page: 103504
  year: 2021
  ident: 6320_CR39
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2021.103504
– volume: 111
  start-page: 147
  issue: 1
  year: 2022
  ident: 6320_CR10
  publication-title: Machine Learning
  doi: 10.1007/s10994-021-06089-1
– ident: 6320_CR27
– ident: 6320_CR72
– volume: 300
  start-page: 103546
  year: 2021
  ident: 6320_CR45
  publication-title: Artificial Intelligence
  doi: 10.1016/j.artint.2021.103546
– volume: 33
  start-page: 16468
  year: 2020
  ident: 6320_CR48
  publication-title: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)
– volume-title: Artificial intelligence: A modern approach
  year: 2009
  ident: 6320_CR60
– ident: 6320_CR24
  doi: 10.1109/ICCV.2017.322
– volume: 33
  start-page: 11525
  year: 2020
  ident: 6320_CR37
  publication-title: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)
– ident: 6320_CR38
– ident: 6320_CR51
– volume: 34
  start-page: 16520
  year: 2021
  ident: 6320_CR49
  publication-title: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)
– ident: 6320_CR16
  doi: 10.1007/978-3-540-78652-8
– ident: 6320_CR59
– ident: 6320_CR13
– volume: 13
  start-page: 245
  issue: 3–4
  year: 1995
  ident: 6320_CR44
  publication-title: New Generation Computing, Special issue on Inductive Logic Programming
  doi: 10.1007/BF03037227
– ident: 6320_CR69
  doi: 10.1109/CVPR46437.2021.00362
– ident: 6320_CR26
  doi: 10.1007/978-3-030-29726-8_1
– volume: 31
  start-page: 38
  issue: 1
  year: 1988
  ident: 6320_CR33
  publication-title: Communications of the ACM
  doi: 10.1145/35043.35046
– volume-title: Algorithmic program debugging
  year: 1983
  ident: 6320_CR63
  doi: 10.7551/mitpress/1192.001.0001
– ident: 6320_CR8
– ident: 6320_CR55
  doi: 10.1109/CVPR.2016.91
– ident: 6320_CR23
  doi: 10.1609/aaai.v32i1.11806
– ident: 6320_CR50
  doi: 10.1609/aaai.v35i18.17931
– ident: 6320_CR61
– ident: 6320_CR1
– volume: 109
  start-page: 1289
  year: 2019
  ident: 6320_CR12
  publication-title: Machine Learning
  doi: 10.1007/s10994-019-05862-7
– ident: 6320_CR42
  doi: 10.3233/FAIA210359
– ident: 6320_CR25
  doi: 10.1109/CVPR.2016.90
– ident: 6320_CR2
  doi: 10.1109/ICCV.2015.279
– volume: 61
  start-page: 1
  year: 2018
  ident: 6320_CR22
  publication-title: Journal of Artificial Intelligence Research
  doi: 10.1613/jair.5714
– ident: 6320_CR56
– ident: 6320_CR20
  doi: 10.24963/ijcai.2017/221
– ident: 6320_CR9
– ident: 6320_CR34
  doi: 10.1007/978-3-319-11558-0_22
– volume: 108
  start-page: 1111
  issue: 7
  year: 2019
  ident: 6320_CR46
  publication-title: Machine Learning
  doi: 10.1007/s10994-018-5750-0
– ident: 6320_CR5
– volume: 15
  start-page: 169
  issue: 2
  year: 2015
  ident: 6320_CR4
  publication-title: Theory and Practice of Logic Programming
  doi: 10.1017/S1471068413000689
– volume: 110
  start-page: 801
  issue: 4
  year: 2021
  ident: 6320_CR11
  publication-title: Machine Learning
  doi: 10.1007/s10994-020-05934-z
– volume: 62
  start-page: 69
  year: 2018
  ident: 6320_CR68
  publication-title: Journal of Artificial Intelligence Research
  doi: 10.1613/jair.1.11203
– ident: 6320_CR15
– ident: 6320_CR29
  doi: 10.1109/CVPR.2017.215
– ident: 6320_CR62
  doi: 10.1609/aaai.v36i8.20795
– ident: 6320_CR65
  doi: 10.24963/ijcai.2019/847
– ident: 6320_CR32
– ident: 6320_CR57
– ident: 6320_CR17
  doi: 10.1007/978-3-031-01574-8
– ident: 6320_CR54
  doi: 10.1007/978-3-540-78469-2_23
– ident: 6320_CR19
– ident: 6320_CR70
  doi: 10.1609/aaai.v35i6.16639
SSID ssj0002686
Score 2.567561
Snippet Deep neural learning has shown remarkable performance at learning representations for visual object categorization. However, deep neural networks such as CNNs...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1465
SubjectTerms Artificial Intelligence
Artificial neural networks
Computer Science
Confounding (Statistics)
Control
Logic programming
Logic programs
Machine Learning
Mechatronics
Natural Language Processing (NLP)
Neural networks
Robotics
Simulation and Modeling
Special Issue on Learning and Reasoning 2022
Visual perception
SummonAdditionalLinks – databaseName: Computer Science Database
  dbid: K7-
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NSwMxEB20evBi_cRqlRy8abDJZnezHhQRi6KUHhR6W5LsBgulrd22_8s_4m8ySbNdFOzFczYh5M28ySaZeQDnStvrpoxhRp2EmRI4kaHExPiSkgGzgcGJTcSdDu_1kq4_cCv8s8qSEx1RZyNlz8ivKDd7mYiZcHI7_sBWNcrernoJjXXYIJQSa-fPMV4yMY2c0qNxpBDbSO6TZnzqnCuKS622gc0iJj8DU7Xb_HVB6uJOu_7fGe_Att9xoruFiezCWj7cg3qp5oC8c-_Dzdfn00v3Gk3fF3IKaN4vZqajLfeUF0gUqBRTMaQgBzlyrIn8A6_iAN7aD6_3j9irK2BFY04wJzrhBpyWplGeaEkF0ZKZtQoEl5qHSraYjHhOgkiwJFOZ-bOIEhFnLGe6pZPgEGrD0TA_AiSCQKhYaNNiiNdwII1CM4i0CnmatIIGkHJpU-VLj1sFjEFaFU22cKQGjtTBkZIGXCz7jBeFN1Z-3SwxSL0TFmkFQAMuSxSr5r9HO1492glsUWc49tljE2rTySw_hU01n_aLyZkzwW9LyN9m
  priority: 102
  providerName: ProQuest
Title αILP: thinking visual scenes as differentiable logic programs
URI https://link.springer.com/article/10.1007/s10994-023-06320-1
https://www.proquest.com/docview/2809964661
Volume 112
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1573-0565
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0002686
  issn: 0885-6125
  databaseCode: P5Z
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1573-0565
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0002686
  issn: 0885-6125
  databaseCode: K7-
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central Database Suite (ProQuest)
  customDbUrl:
  eissn: 1573-0565
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0002686
  issn: 0885-6125
  databaseCode: BENPR
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 1573-0565
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0002686
  issn: 0885-6125
  databaseCode: M2P
  dateStart: 20230101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerLINK Contemporary 1997-Present
  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/eLvHCXMwnV1LSwMxEB60evBifWK1lhy86UI3m93NehBUWhS1LPVB8bIk6QYLpUq37f_yj_ibnKS7rYoKesklyRBmMo-QmfkADpQ2301d5jBqIcyUcCLpS8dFXVLSY8YxWLCJsNXinU4U50VhWZHtXnxJWkv9odjNtrGlBo3A1P3im2cJ3R036ti-fZjZXxpYfEdUH98x_jsvlfmexmd3NI8xv3yLWm_TLP_vnGuwmkeX5HR6HdZhIR1sQLlAbiC5Im_Cydvr5XV8TEZPU-gEMullY9xoWjulGREZKYBT0ADIfkqshSR5Mle2BffNxt35hZMjKTiKhtx1uKsjjoKoaxqkkZZUuFoy5JAnuNTcV7LOZMBT1wsEi7qqi6-IIBJhl6VM13XkbUNp8DxId4AIzxMqFBpn0MiivaOBj0SkQcPTbt2rgFswNFF5m3GDdtFP5g2SDYMSZFBiGZS4FTic7XmZNtn4dXW1kFOSK1yWUI7LAobRRgWOCrnMp3-mtvu35XuwQq1oTcpjFUqj4Tjdh2U1GfWyYQ2WzhqtuF2DxavQwfGGxjjG_mPNXtF3ZxPZ4Q
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1NTxsxEB2hgNRemtIPEQjFh_bUWo29zq4XCaqqEBEljThQKbet7bXVSFECbBLEn0Lij_CbGDu7RK1Ubhw4ez3a3Rm_mV173gP4aJzfbsoFFTxImBlFU93WlOFaMjoSPjEEsYlkMJDDYXq6BjdVL4w_VllhYgDqfGr8P_KvXGItEwtMJ9_OL6hXjfK7q5WExjIsevb6Cj_ZioPuEfr3E-ed47MfJ7RUFaCGJ5JRyVwq8aZajsc2dZor5rTAxRYpqZ1sG90SOpaWRbESaW5yrKjjVCW5sMK1nCdfQshfF5FMPFd_L6EPyM_joCyJttrUVw5lk07ZqhdIeLnXUvBdy-zvRLiqbv_ZkA15rlN_bm_oNbwqK2ryfbkENmHNTt5AvVKrICV4vYXDu9tu_3SfzP4s5SLIYlTMcaKns7IFUQWpxGIQ9PTYkpAVSHmArXgHv57kKd5DbTKd2C0gKoqUSZTDEUwsiPE8bqMR7RUAHWtFDWCVKzNTUqt7hY9xtiKF9u7P0P1ZcH_GGvD5Yc75kljk0aublc-zEmSKbOXwBnypomY1_H9r249b24MXJ2c_-1m_O-jtwEsegtYf8WxCbXY5t7uwYRazUXH5IYQ_gd9PHU33THY8Ww
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3NThsxEB4hqFAvpEArArT4QE9gEXu9f0hQVaURUVCUA0jctrbXFkgoCWwI4rG49iH6TIwdL1GR4MaBs9ej3Z1vfnY9Mx_AtrbuuKkUVHBPYaYlzVWsKENb0ioSLjB4som018vOz_P-HPyte2FcWWXtE72jLofa_SPf4xnmMonAcLJnQ1lE_6j9Y3RNHYOUO2mt6TSmEOma-zv8fKsOOkeo6--ct3-f_jqmgWGAap5mjGbM5hneYMvyxORWccmsEmh4kcyUzWKtWkIlmWFRIkVe6hKz6ySXaSmMsC3rBjGh-1_AKBw7G-um9CkK8MSzTKKsmLosIjTshLY9P5CXO14F18HM_g-Ks0z32eGsj3ntxnt-W59gKWTa5OfUNJZhzgxWoFGzWJDg1Fbh8N9D56S_T8YXUxoJMrmsbnGjG3NlKiIrUpPIoDNUV4b4aEFCYVv1Gc7e5Cm-wPxgODBrQGQUSZ1KiysYcND38yRGIcoxA1rWiprAarUWOoxcd8wfV8VsWLSDQoFQKDwUCtaEnac9o-nAkVev3qz1XwTnUxUz5Tdht0bQbPllaeuvS9uCRQRRcdLpdTfgI_f4dZWfmzA_vrk1X-GDnowvq5tv3hII_HlrMD0Cc5ZFFQ
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=alpha%24%24ILP%3A+thinking+visual+scenes+as+differentiable+logic+programs&rft.jtitle=Machine+learning&rft.au=Shindo%2C+Hikaru&rft.au=Pfanschilling%2C+Viktor&rft.au=Dhami%2C+Devendra+Singh&rft.au=Kersting%2C+Kristian&rft.date=2023-05-01&rft.issn=0885-6125&rft.eissn=1573-0565&rft.volume=112&rft.issue=5&rft.spage=1465&rft.epage=1497&rft_id=info:doi/10.1007%2Fs10994-023-06320-1&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s10994_023_06320_1
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