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 vectors, while predicates are interpreted in fuzzy sets. In real logic it is possible to formally define the following two tasks: (i) learning from data in presence of logical constraints, and (ii) reasoning on formulas exploiting concrete data. We implement real logic in an deep learning architecture, called logic tensor networks, based on Google’s \(\textsc {TensorFlow}^{\tiny {\text {TM}}}\) primitives. The paper concludes with experiments on a simple but representative example of knowledge completion.
The first author acknowledges the Mobility Program of FBK, for supporting a long term visit at City University London. He also acknowledges NVIDIA Corporation for supporting this research with the donation of a GPU. We also thank Prof. Marco Gori and his group at the University of Siena for the generous and inspiring discussions on the topic of integrating logical reasoning and statistical machine learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
In logic, the term “grounding” indicates the operation of replacing the variables of a term/formula with constants, or terms that do not contains other variables. To avoid confusion, we use the synonym “instantiation” for this sense.
- 2.
- 3.
Normally, a probabilistic approach is taken to solve this problem, and one that requires instantiating all clauses to remove variables, essentially turning the problem into a propositional one; ltn takes a different approach.
- 4.
Notice how no grounding is provided about the signature of the knowledge-base.
- 5.
A smoth factor \(\lambda ||\mathbf {\Omega }||^2_2\) is added to the loss to limit the size of parameters.
- 6.
\(\mu (a,b) = \min (1,a+b)\).
References
Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2, 1–127 (2009)
Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484–503 (2016)
Kephart, J.O., Chess, D.M.: The vision of autonomic computing. Computer 36, 41–50 (2003)
Kiela, D., Bottou, L.: Learning image embeddings using convolutional neural networks for improved multi-modal semantics. In: Proceedings of EMNLP 2014 (2014)
Socher, R., Chen, D., Manning, C.D., Ng, A.: Reasoning with neural tensor networks for knowledge base completion. In: Advances in Neural Information Processing Systems, pp. 926–934 (2013)
Guha, R.: Towards a model theory for distributed representations. In: 2015 AAAI Spring Symposium Series (2015)
Bottou, L.: From machine learning to machine reasoning. Technical report, arXiv.1102.1808 (2011)
d’Avila Garcez, A.S., Lamb, L.C., Gabbay, D.M.: Neural-Symbolic Cognitive Reasoning. Cognitive Technologies. Springer, Heidelberg (2009)
Diligenti, M., Gori, M., Maggini, M., Rigutini, L.: Bridging logic and kernel machines. Mach. Learn. 86, 57–88 (2012)
Barrett, L., Feldman, J., MacDermed, L.: A (somewhat) new solution to the variable binding problem. Neural Comput. 20, 2361–2378 (2008)
Bergmann, M.: An Introduction to Many-Valued and Fuzzy Logic: Semantics, Algebras, and Derivation Systems. Cambridge University Press, New York (2008)
TensorFlow: Large-scale machine learning on heterogeneous systems (2016). tensorflow.org
d’Avila Garcez, A.S., Gori, M., Hitzler, P., Lamb, L.C.: Neural-symbolic learning and reasoning (dagstuhl seminar 14381). Dagstuhl Rep. 4, 50–84 (2014)
McCallum, A., Gabrilovich, E., Guha, R., Murphy, K. (eds.): Knowledge representation and reasoning: integrating symbolic and neural approaches. In: AAAI Spring Symposium, Stanford University, CA, USA (2015)
Besold, T.R., d’Avila Garcez, A., Marcus, G.F., Miikulainen, R. (eds.): Cognitive computation: integrating neural and symbolic approaches. In: Workshop at NIPS 2015, Montreal, Canada, CEUR-WS 1583, April 2016
Huth, M., Ryan, M.: Logic in Computer Science: Modelling and Reasoning About Systems. Cambridge University Press, New York (2004)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent Dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Brys, T., Drugan, M.M., Bosman, P.A., De Cock, M., Nowé, A.: Solving satisfiability in fuzzy logics by mixing CMA-ES. In: Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013, pp. 1125–1132. ACM, New York (2013)
Richardson, M., Domingos, P.: Markov logic networks. Mach. Learn. 62, 107–136 (2006)
Tieleman, T., Hinton, G.: Lecture 6.5 - RMSProp, COURSERA: Neural networks for machine learning. Technical report (2012)
Wang, J., Domingos, P.M.: Hybrid markov logic networks. In: AAAI, pp. 1106–1111 (2008)
Nath, A., Domingos, P.M.: Learning relational sum-product networks. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, January 25–30, 2015, Austin, Texas, USA, pp. 2878–2886 (2015)
Kosko, B.: Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence. Prentice-Hall Inc., Upper Saddle River (1992)
Milch, B., Marthi, B., Russell, S.J., Sontag, D., Ong, D.L., Kolobov, A.: BLOG: probabilistic models with unknown objects. In: IJCAI 2005, pp. 1352–1359 (2005)
Raedt, L.D., Kersting, K., Natarajan, S., Poole, D.: Statistical Relational Artificial Intelligence: Logic, Probability, and Computation. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool, San Rafael (2016)
Muggleton, S.H., Lin, D., Tamaddoni-Nezhad, A.: Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited. Mach. Learn. 100, 49–73 (2015)
França, M.V.M., Zaverucha, G., d’Avila Garcez, A.S.: Fast relational learning using bottom clause propositionalization with artificial neural networks. Mach. Learn. 94, 81–104 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Serafini, L., d’Avila Garcez, A.S. (2016). Learning and Reasoning with Logic Tensor Networks. In: Adorni, G., Cagnoni, S., Gori, M., Maratea, M. (eds) AI*IA 2016 Advances in Artificial Intelligence. AI*IA 2016. Lecture Notes in Computer Science(), vol 10037. Springer, Cham. https://doi.org/10.1007/978-3-319-49130-1_25
Download citation
DOI: https://doi.org/10.1007/978-3-319-49130-1_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-49129-5
Online ISBN: 978-3-319-49130-1
eBook Packages: Computer ScienceComputer Science (R0)