A connectionist inductive learning system for modal logic programming

A. S. D'Avila Garcez; L. C. Lamb; D. M. Gabbay

doi:10.1109/ICONIP.2002.1199022

A connectionist inductive learning system for modal logic programming

A. S. D'Avila Garcez, L. C. Lamb, D. M. Gabbay

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

Neural-Symbolic integration has become a very active research area in the last decade. In this paper, we present a new massively parallel model for modal logic. We do so by extending the language of Modal Prolog to allow modal operators in the head of the clauses. We then use an ensemble of C-IL²p neural networks to encode the extended modal theory (and its relations), and show that the ensemble computes a fixpoint semantics of the extended theory. An immediate result of our approach is the ability to perform learning from examples efficiently using each network of the ensemble. Therefore, one can adapt the extended C-IL²P system by training possible world representations.

Original language	English
Title of host publication	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Subtitle of host publication	Computational Intelligence for the E-Age
Editors	Kunihiko Fukushima, Lipo Wang, Jagath C. Rajapakse, Soo-Young Lee, Xin Yao
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1992-1997
Number of pages	6
ISBN (Electronic)	9810475241, 9789810475246
DOIs	https://doi.org/10.1109/ICONIP.2002.1199022
State	Published - 2002
Externally published	Yes
Event	9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore Duration: 18 Nov 2002 → 22 Nov 2002

Publication series

Name	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
Volume	4

Conference

Conference	9th International Conference on Neural Information Processing, ICONIP 2002
Country/Territory	Singapore
City	Singapore
Period	18/11/02 → 22/11/02

Bibliographical note

Publisher Copyright:
© 2002 Nanyang Technological University.

Keywords

Change of Representation
Hybrid Systems
Modal Logic
Neural-Symbolic Integration

Access to Document

10.1109/ICONIP.2002.1199022

Cite this

D'Avila Garcez, A. S., Lamb, L. C., & Gabbay, D. M. (2002). A connectionist inductive learning system for modal logic programming. In K. Fukushima, L. Wang, J. C. Rajapakse, S.-Y. Lee, & X. Yao (Eds.), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age (pp. 1992-1997). Article 1199022 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age; Vol. 4). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICONIP.2002.1199022

D'Avila Garcez, A. S. ; Lamb, L. C. ; Gabbay, D. M. / A connectionist inductive learning system for modal logic programming. ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. editor / Kunihiko Fukushima ; Lipo Wang ; Jagath C. Rajapakse ; Soo-Young Lee ; Xin Yao. Institute of Electrical and Electronics Engineers Inc., 2002. pp. 1992-1997 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age).

@inproceedings{9fb18437fc9a4aceb5162040d5946827,

title = "A connectionist inductive learning system for modal logic programming",

abstract = "Neural-Symbolic integration has become a very active research area in the last decade. In this paper, we present a new massively parallel model for modal logic. We do so by extending the language of Modal Prolog to allow modal operators in the head of the clauses. We then use an ensemble of C-IL2p neural networks to encode the extended modal theory (and its relations), and show that the ensemble computes a fixpoint semantics of the extended theory. An immediate result of our approach is the ability to perform learning from examples efficiently using each network of the ensemble. Therefore, one can adapt the extended C-IL2P system by training possible world representations.",

keywords = "Change of Representation, Hybrid Systems, Modal Logic, Neural-Symbolic Integration",

author = "\{D'Avila Garcez\}, \{A. S.\} and Lamb, \{L. C.\} and Gabbay, \{D. M.\}",

note = "Publisher Copyright: {\textcopyright} 2002 Nanyang Technological University.; 9th International Conference on Neural Information Processing, ICONIP 2002 ; Conference date: 18-11-2002 Through 22-11-2002",

year = "2002",

doi = "10.1109/ICONIP.2002.1199022",

language = "אנגלית",

series = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1992--1997",

editor = "Kunihiko Fukushima and Lipo Wang and Rajapakse, \{Jagath C.\} and Soo-Young Lee and Xin Yao",

booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing",

address = "ארצות הברית",

}

D'Avila Garcez, AS, Lamb, LC & Gabbay, DM 2002, A connectionist inductive learning system for modal logic programming. in K Fukushima, L Wang, JC Rajapakse, S-Y Lee & X Yao (eds), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age., 1199022, ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age, vol. 4, Institute of Electrical and Electronics Engineers Inc., pp. 1992-1997, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, Singapore, 18/11/02. https://doi.org/10.1109/ICONIP.2002.1199022

A connectionist inductive learning system for modal logic programming. / D'Avila Garcez, A. S.; Lamb, L. C.; Gabbay, D. M.
ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. ed. / Kunihiko Fukushima; Lipo Wang; Jagath C. Rajapakse; Soo-Young Lee; Xin Yao. Institute of Electrical and Electronics Engineers Inc., 2002. p. 1992-1997 1199022 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age; Vol. 4).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A connectionist inductive learning system for modal logic programming

AU - D'Avila Garcez, A. S.

AU - Lamb, L. C.

AU - Gabbay, D. M.

PY - 2002

Y1 - 2002

N2 - Neural-Symbolic integration has become a very active research area in the last decade. In this paper, we present a new massively parallel model for modal logic. We do so by extending the language of Modal Prolog to allow modal operators in the head of the clauses. We then use an ensemble of C-IL2p neural networks to encode the extended modal theory (and its relations), and show that the ensemble computes a fixpoint semantics of the extended theory. An immediate result of our approach is the ability to perform learning from examples efficiently using each network of the ensemble. Therefore, one can adapt the extended C-IL2P system by training possible world representations.

AB - Neural-Symbolic integration has become a very active research area in the last decade. In this paper, we present a new massively parallel model for modal logic. We do so by extending the language of Modal Prolog to allow modal operators in the head of the clauses. We then use an ensemble of C-IL2p neural networks to encode the extended modal theory (and its relations), and show that the ensemble computes a fixpoint semantics of the extended theory. An immediate result of our approach is the ability to perform learning from examples efficiently using each network of the ensemble. Therefore, one can adapt the extended C-IL2P system by training possible world representations.

KW - Change of Representation

KW - Hybrid Systems

KW - Modal Logic

KW - Neural-Symbolic Integration

UR - https://www.scopus.com/pages/publications/84966330311

U2 - 10.1109/ICONIP.2002.1199022

DO - 10.1109/ICONIP.2002.1199022

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:84966330311

T3 - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age

SP - 1992

EP - 1997

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing

A2 - Fukushima, Kunihiko

A2 - Wang, Lipo

A2 - Rajapakse, Jagath C.

A2 - Lee, Soo-Young

A2 - Yao, Xin

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Conference on Neural Information Processing, ICONIP 2002

Y2 - 18 November 2002 through 22 November 2002

ER -

D'Avila Garcez AS, Lamb LC, Gabbay DM. A connectionist inductive learning system for modal logic programming. In Fukushima K, Wang L, Rajapakse JC, Lee SY, Yao X, editors, ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Institute of Electrical and Electronics Engineers Inc. 2002. p. 1992-1997. 1199022. (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age). doi: 10.1109/ICONIP.2002.1199022

A connectionist inductive learning system for modal logic programming

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this