More Web Proxy on the site http://driver.im/

research-article

Learning and reasoning in logic tensor networks: theory and application to semantic image interpretation

Authors:

Luciano Serafini,

Ivan Donadello,

Artur d'Avila GarcezAuthors Info & Claims

SAC '17: Proceedings of the Symposium on Applied Computing

Pages 125 - 130

https://doi.org/10.1145/3019612.3019642

Published: 03 April 2017 Publication History

Abstract

This paper presents a revision of Real Logic and its implementation with Logic Tensor Networks and its application to Semantic Image Interpretation. Real Logic is a framework where learning from numerical data and logical reasoning are integrated using first order logic syntax. The symbols of the signature of Real Logic are interpreted in the data-space, i.e, on the domain of real numbers. The integration of learning and reasoning obtained in Real Logic allows us to formalize learning as approximate satisfiability in the presence of logical constraints, and to perform inference on symbolic and numerical data. After introducing a refined version of the formalism, we describe its implementation into Logic Tensor Networks which uses deep learning within Google's TensorFlow™. We evaluate LTN on the task of classifying objects and their parts in images, where we combine state-of-the-art-object detectors with a part-of ontology. LTN outperforms the state-of-the-art on object classification, and improves the performances on part-of relation detection with respect to a rule-based baseline.

References

[1]

M. Bergmann. An Introduction to Many-Valued and Fuzzy Logic: Semantics, Algebras, and Derivation Systems. Cambridge University Press, 2008.

[2]

T. R. Besold, A. d'Avila Garcez, G. F. Marcus, and R. Miikulainen, editors. Cognitive Computation: Integrating Neural and Symbolic Approaches, Workshop at NIPS 2015, April 2016. CEUR-WS 1583.

[3]

X. Chen, R. Mottaghi, X. Liu, S. Fidler, R. Urtasun, and A. Yuille. Detect what you can: Detecting and representing objects using holistic models and body parts. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

Digital Library

[4]

A. S. d'Avila Garcez, L. C. Lamb, and D. M. Gabbay. Neural-Symbolic Cognitive Reasoning. Cognitive Technologies. Springer, 2009.

Digital Library

[5]

M. Diligenti, M. Gori, M. Maggini, and L. Rigutini. Bridging logic and kernel machines. Machine Learning, 86(1):57--88, 2012.

Digital Library

[6]

C. Fellbaum, editor. WordNet: an electronic lexical database. MIT Press, 1998.

[7]

M. V. M. França, G. Zaverucha, and A. S. d'Avila Garcez. Fast relational learning using bottom clause propositionalization with artificial neural networks. Machine Learning, 94(1):81--104, 2014.

Digital Library

[8]

R. Girshick. Fast r-cnn. In International Conference on Computer Vision (ICCV), 2015.

Digital Library

[9]

N. Guarino and G. Guizzardi. On the reification of relationships. In 24th Italian Symposium on Advanced Database Systems, SEBD, pages 350--357, 2016.

[10]

R. Guha. Towards a model theory for distributed representations. In AAAI Spring Symposium Series, 2015.

[11]

B. Gutmann, M. Jaeger, and L. De Raedt. Extending problog with continuous distributions. In International Conference on Inductive Logic Programming, pages 76--91. Springer, 2010.

Digital Library

[12]

K. Kersting and L. De Raedt. Adaptive bayesian logic programs. In International Conference on Inductive Logic Programming, pages 104--117. Springer, 2001.

Digital Library

[13]

B. Kosko. Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence. Prentice-Hall, Inc., 1992.

Digital Library

[14]

R. Krishna, Y. Zhu, O. Groth, J. Johnson, K. Hata, J. Kravitz, S. Chen, Y. Kalantidis, L.-J. Li, D. A. Shamma, M. Bernstein, and L. Fei-Fei. Visual genome: Connecting language and vision using crowdsourced dense image annotations, 2016.

[15]

B. Milch, B. Marthi, S. J. Russell, D. Sontag, D. L. Ong, and A. Kolobov. BLOG: probabilistic models with unknown objects. In IJCAI, 2005.

Digital Library

[16]

S. H. Muggleton, D. Lin, and A. Tamaddoni-Nezhad. Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited. Machine Learning, 100(1):49--73, 2015.

Digital Library

[17]

P. Narman, M. Buschle, J. Konig, and P. Johnson. Hybrid probabilistic relational models for system quality analysis. In Enterprise Distributed Object Computing Conference (EDOC), 2010 14th IEEE International, pages 57--66. IEEE, 2010.

Digital Library

[18]

A. Nath and P. M. Domingos. Learning relational sum-product networks. In AAAI, 2015.

Digital Library

[19]

L. D. Raedt, K. Kersting, S. Natarajan, and D. Poole. Statistical Relational Artificial Intelligence: Logic, Probability, and Computation. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, 2016.

Digital Library

[20]

I. Ravkic, J. Ramon, and J. Davis. Learning relational dependency networks in hybrid domains. Machine Learning, 100(2--3):217--254, 2015.

Digital Library

[21]

M. Richardson and P. Domingos. Markov logic networks. Mach. Learn., 62(1--2):107--136, Feb. 2006.

Digital Library

[22]

L. Serafini and A. S. d'Avila Garcez. Learning and reasoning with logic tensor networks. In AI*IA 2016: XVth International Conference of the Italian Association for Artificial Intelligence, Genova, Italy, pages 334--348, 2016.

Digital Library

[23]

R. Socher, D. Chen, C. D. Manning, and A. Ng. Reasoning with neural tensor networks for knowledge base completion. In Advances in Neural Information Processing Systems, pages 926--934, 2013.

Digital Library

[24]

S. Teso, R. Sebastiani, and A. Passerini. Hybrid srl with optimization modulo theories. arXiv preprint arXiv:1402.4354, 2014.

[25]

T. Tieleman and G. Hinton. Lecture 6.5 - RMSProp, COURSERA: Neural networks for machine learning. Technical report, 2012.

[26]

J. Wang and P. M. Domingos. Hybrid markov logic networks. In AAAI, volume 8, pages 1106--1111, 2008.

Digital Library

Cited By

Mileo A(2024)Towards a neuro-symbolic cycle for human-centered explainabilityNeurosymbolic Artificial Intelligence10.3233/NAI-240740(1-13)Online publication date: 28-Aug-2024
https://doi.org/10.3233/NAI-240740
Renkhoff JFeng KMeier-Doernberg MVelasquez ASong H(2024)A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial IntelligenceIEEE Transactions on Artificial Intelligence10.1109/TAI.2024.33517985:8(3765-3779)Online publication date: Aug-2024
https://doi.org/10.1109/TAI.2024.3351798
Apicella ACorazza AIsgrò FPrevete R(2023)Toward the Improvement of Probabilistic Classifiers Using Ontologies2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE)10.1109/MetroXRAINE58569.2023.10405834(664-669)Online publication date: 25-Oct-2023
https://doi.org/10.1109/MetroXRAINE58569.2023.10405834
Show More Cited By

Index Terms

Learning and reasoning in logic tensor networks: theory and application to semantic image interpretation
1. Computing methodologies
  1. Artificial intelligence
    1. Knowledge representation and reasoning
      1. Vagueness and fuzzy logic
  2. Machine learning
    1. Machine learning approaches
      1. Logical and relational learning
        Statistical relational learning
      2. Neural networks

Recommendations

Learning and Reasoning with Logic Tensor Networks
AI*IA 2016 Advances in Artificial Intelligence
Abstract
The paper introduces real logic: a framework that seamlessly integrates logical deductive reasoning with efficient, data-driven relational learning. Real logic is based on full first order language. Terms are interpreted in n-dimensional feature ...
Undefinability in Inquisitive Logic with Tensor
Logic, Rationality, and Interaction
Abstract
Logics based on team semantics, such as inquisitive logic and dependence logic, are not closed under uniform substitution. This leads to an interesting separation between expressive power and definability: it may be that an operator O can be added ...
Automated Reasoning in Higher-order Logic: Set Comprehension and Extensionality in Church's Type Theory

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

SAC '17: Proceedings of the Symposium on Applied Computing

April 2017

2004 pages

ISBN:9781450344869

DOI:10.1145/3019612

Conference Chair:
Sung Y. Shin
South Dakota State University
,
Program Chairs:
Dongwan Shin
New Mexico Tech
,
Maria Lencastre
University of Pernambuco, Brazil

Copyright © 2017 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGAPP: ACM Special Interest Group on Applied Computing

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 03 April 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

SAC 2017

Sponsor:

SIGAPP

SAC 2017: Symposium on Applied Computing

April 3 - 7, 2017

Marrakech, Morocco

Acceptance Rates

Overall Acceptance Rate 1,650 of 6,669 submissions, 25%

Upcoming Conference

SAC '25

Sponsor:
sigapp

The 40th ACM/SIGAPP Symposium on Applied Computing

March 31 - April 4, 2025

Catania , Italy

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

21
Total Citations
View Citations
484
Total Downloads

Downloads (Last 12 months)29
Downloads (Last 6 weeks)4

Reflects downloads up to 30 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Mileo A(2024)Towards a neuro-symbolic cycle for human-centered explainabilityNeurosymbolic Artificial Intelligence10.3233/NAI-240740(1-13)Online publication date: 28-Aug-2024
https://doi.org/10.3233/NAI-240740
Renkhoff JFeng KMeier-Doernberg MVelasquez ASong H(2024)A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial IntelligenceIEEE Transactions on Artificial Intelligence10.1109/TAI.2024.33517985:8(3765-3779)Online publication date: Aug-2024
https://doi.org/10.1109/TAI.2024.3351798
Apicella ACorazza AIsgrò FPrevete R(2023)Toward the Improvement of Probabilistic Classifiers Using Ontologies2023 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE)10.1109/MetroXRAINE58569.2023.10405834(664-669)Online publication date: 25-Oct-2023
https://doi.org/10.1109/MetroXRAINE58569.2023.10405834
Stockton PDavis CJohn E(2023)Microarchitecture Characterization and Analysis of Emerging Neuro-Symbolic A.I. Workloads2023 International Conference on Computational Science and Computational Intelligence (CSCI)10.1109/CSCI62032.2023.00011(23-29)Online publication date: 13-Dec-2023
https://doi.org/10.1109/CSCI62032.2023.00011
Giannini FDiligenti MMaggini MGori MMarra G(2023)T-norms driven loss functions for machine learningApplied Intelligence10.1007/s10489-022-04383-653:15(18775-18789)Online publication date: 9-Feb-2023
https://doi.org/10.1007/s10489-022-04383-6
Alessandro RFrancesco MFabrizio LLia M(2023)L-TReiD: Logic Tensor Transformer for Re-identificationAdvances in Visual Computing10.1007/978-3-031-47966-3_27(345-357)Online publication date: 3-Dec-2023
https://doi.org/10.1007/978-3-031-47966-3_27
KÖRNER PLEUSCHEL MBARBOSA JCOSTA VDAHL VHERMENEGILDO MMORALES JWIELEMAKER JDIAZ DABREU SCIATTO G(2022)Fifty Years of Prolog and BeyondTheory and Practice of Logic Programming10.1017/S147106842200010222:6(776-858)Online publication date: 17-May-2022
https://doi.org/10.1017/S1471068422000102
Stehr MKim MTalcott C(2022)A probabilistic approximate logic for neuro-symbolic learning and reasoningJournal of Logical and Algebraic Methods in Programming10.1016/j.jlamp.2021.100719124(100719)Online publication date: Jan-2022
https://doi.org/10.1016/j.jlamp.2021.100719
Kautz H(2022)The third AI summerAI Magazine10.1002/aaai.1203643:1(105-125)Online publication date: 31-Mar-2022
https://dl.acm.org/doi/10.1002/aaai.12036
Roychowdhury SDiligenti MGori M(2021)Regularizing deep networks with prior knowledge: A constraint-based approachKnowledge-Based Systems10.1016/j.knosys.2021.106989(106989)Online publication date: Apr-2021
https://doi.org/10.1016/j.knosys.2021.106989
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten