This chapter presents an approach to learn first-order logical theories with neural networks. We discuss representation issues for this task in terms of a variable-free representation of predicate logic using topos theory and the possibility to use automatically generated equations (induced by the topos) as input for a neural network. Besides the translation of first-order logic into a variable-free representation, a programming language fragment for representing variable-free logic, the structure of the used neural network for learning, and the overall architecture of the system are discussed. Finally, an evaluation of the approach is presented by applying the framework to theorem proving problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barnden J. A. (1989). Neural net implementation of complex symbol process-ing in a mental model approach to syllogistic reasoning, in Proceedings of the International Joint Conference on Artificial Intelligence, 568-573.
Shastri L., Ajjanagadde V. (1990). From simple associations to systematic reasoning: A connectionist representation of rules, variables and dynamic bindings using temporal synchrony, Behavioral and Brain Sciences 16: 417-494.
Pollack J. (1990). Recursive Distributed Representations Artificial Intelligence 46(1):77-105.
Rojas, R. (1996). Neural Networks - A Systematic Introduction, Springer, Berlin, New York.
Steinbach B., Kohut R. (2002). Neural Networks - A Model of Boolean Functions. In Steinbach B (ed.): Boolean Problems, Proceedings of the 5th Interna- tional Workshop on Boolean Problems, 223-240, Freiberg.
Lange T., Dyer M. G. (1989). High-level inferencing in a connectionist network. Technical report UCLA-AI-89-12.
Smolenski P. (1990). Tensor product variable binding and the representation of symbolic structures in connectionist systems, Artificial Intelligence 46(1-2): 159-216.
Plate T. (1994). Distributed Representations and Nested Compositional Structure. PhD thesis, University of Toronto.
Hitzler P., Hölldobler S., Seda A. (2004). Logic programs and connectionist networks. Journal of Applied Logic, 2(3):245-272.
Healy M., Caudell T. (2004). Neural Networks, Knowledge and Cognition: A Mathematical Semantic Model Based upon Category Theory, University of New Mexico, EECE-TR-04-020.
D’Avila Garcez A., Broda K., Gabbay D. (2002). Neural-Symbolic Learning Systems: Foundations and Applications. Springer-Verlag.
Gust H., Kühnberger K.-U. (2004). Cloning Composition and Logical Infer-ence in Neural Networks Using Variable-Free Logic. In: AAAI Fall Symposium Series 2004, Symposium: Compositional Connectionism in Cognitive Science, Washington D.C., 25-30.
Gust H., Kühnberger K.-U. (2005.) Learning Symbolic Inferences with Neural Networks. In: Bara B., Barsalou L., Bucciarelli M. (eds): CogSci 2005, XXVII Annual Conference of the Cognitive Science Society. Lawrence Erlbaum, 875-880.
Goldblatt R. (1979). Topoi: The Categorial Analysis of Logic. Studies in Logic and the Foundations of Mathematics, 98 (1979), North-Holland, Amsterdam.
Montague R. (1970). Pragmatics and intensional logic. Synthèse 22:68-94. Reprinted in: Formal Philosophy. Selected Papers of Richard Montague. Edited and with an introduction by Richmond H. Thomason. New Haven/London: Yale University Press, 1974, 119-147.
Rydeheard D. E., Burstall R. M. (1988). Computational Category Theory, Prentice Hall.
Gust H. (2000). Quantificational Operators and their Interpretation as Higher Order Operators. In Böttner M., Thümmel W. (eds) Variable-free Semantics. Secolo, Osnabrück, 132-161.
Gust H. (2006). A sorted logical language with variable patterns. In Bab, S, Gulden, J, Noll, T, Wieczorek, T (eds): Models and Human Reasoning, Wis-senschaft und Technik Verlag, Berlin, 35-62.
Walter C. (1985). A Mechanical Solution of Schubert’s Steamroller by Many-Sorted Resolution. Artificial Intelligence 26: 217-224.
Urquhart A. (2001). Basic many-valued logic. In Gabbay D., Guenthner F. (eds.), Handbook of Philosophical Logic, 2nd ed., vol. 2, Kluwer Acad. Publ., Dordrecht, pp. 249-295.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Gust, H., Kühnberger, KU., Geibel, P. (2007). Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory. In: Hammer, B., Hitzler, P. (eds) Perspectives of Neural-Symbolic Integration. Studies in Computational Intelligence, vol 77. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73954-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-73954-8_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73953-1
Online ISBN: 978-3-540-73954-8
eBook Packages: EngineeringEngineering (R0)