Three notable hallmarks of intelligent cognition are the ability to draw rational conclusions, the ability to make plausible assumptions, and the ability to generalise from experience. Although human cognition often involves the interaction of these three abilities, in Artificial Intelligence they are typically studied in isolation. In our research programme, we seek to integrate the three abilities within neural computation, offering a unified framework for learning and reasoning that exploits the parallelism and robustness of connectionism. A neural network can be the machine for computation, inductive learning, and effective reasoning, while logic provides rigour, modularity, and explanation capability to the network. We call such systems, combining a connectionist learning component with a logical reasoning component, neural-symbolic learning systems. In what follows, I review the work on neural-symbolic learning systems, starting with logic programming and then looking at how to represent modal logic and other forms of non-classical reasoning in neural networks. The model consists of a network ensemble, each network representing the knowledge of an agent (or possible world) at a particular time point. Ensembles may be seen as in different levels of abstraction so that networks may be fibred onto (combined with) other networks to form a structure combining different logical systems or, for example, object-level and meta-level knowledge. We claim that this quite powerful yet simple structure offers a basis for an expressive yet computationally tractable cognitive model of integrated reasoning and learning.
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
d’Avila Garcez, A.S.: Fewer epistemological challenges for connectionism. In Cooper, S.B., Lowe, B., Torenvliet, L., eds.: Proceedings of Computabil-ity in Europe, CiE 2005. Volume LNCS 3526., Amsterdam, The Netherlands, Springer-Verlag (2005) 139-149
d’Avila Garcez, A.S., Gabbay, D.M., Ray, O., Woods, J.: Abductive reasoning in neural-symbolic systems. TOPOI: An International Review of Philosophy (2007) doi:10.1007/s11245-006-9005-5.
Valiant, L.G.: Three problems in computer science. Journal of the ACM 50 (2003) 96-99
d’Avila Garcez, A.S., Broda, K., Gabbay, D.M.: Neural-Symbolic Learning Systems: Foundations and Applications. Perspectives in Neural Computing. Springer-Verlag (2002)
d’Avila Garcez, A.S., Lamb, L.C., Gabbay, D.M.: Connectionist modal logic: Representing modalities in neural networks. Theoretical Computer Science 371 (2007) 34-53
d’Avila Garcez, A.S., Lamb, L.C., Gabbay, D.M.: Connectionist computations of intuitionistic reasoning. Theoretical Computer Science 358 (2006) 34-55
d’Avila Garcez, A.S., Lamb, L.C.: A connectionist computational model for epistemic and temporal reasoning. Neural Computation 18 (2006) 1711-1738
d’Avila Garcez, A.S., Gabbay, D.M.: Fibring neural networks. In: Proceedings of 19th National Conference on Artificial Intelligence AAAI’04, San Jose, California, USA, AAAI Press (2004) 342-347
McCarthy, J.: Epistemological challenges for connectionism. Behaviour and Brain Sciences 11 (1988) 44
Smolensky, P.: On the proper treatment of connectionism. Behavioral and Brain Sciences 11 (1988) 1-74
Gardenfors, P.: Conceptual Spaces: The Geometry of Thought. MIT Press (2000)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall (1999)
Bader, S., d’Avila Garcez, A.S., Hitzler, P.: Computing first order logic programs by fibring artificial neural networks. In: Proceedings of International FLAIRS Conference, Florida, USA, AAAI Press (2005) 314-319
Bader, S., Hitzler, P., Hölldobler, S., Witzel, A.: A fully connectionist model generator for covered first-order logic programs. In: M. Veloso, ed.: Proceedings of International Joint Conference on Artificial Intelligence IJCAI07, Hyderabad, India (2007) 666-671
Hölldobler, S.: Automated inferencing and connectionist models. Postdoctoral Thesis, Intellektik, Informatik, TH Darmstadt (1993)
Shastri, L., Ajjanagadde, V.: A connectionist representation of rules, variables and dynamic binding. Technical report, Dept of Computer and Information Science, University of Pennsylvania (1990)
Bologna, G.: Is it worth generating rules from neural network ensembles? Journal of Applied Logic 2 (2004) 325-348
d’Avila Garcez, A.S., Broda, K., Gabbay, D.M.: Symbolic knowledge extraction from trained neural networks: A sound approach. Artificial Intelligence 125 (2001) 155-207
d’Avila Garcez, A.S., Zaverucha, G.: The connectionist inductive learning and logic programming system. Applied Intelligence 11 (1999) 59-77
Hitzler, P., Hölldobler, S., Seda, A.K.: Logic programs and connectionist networks. Journal of Applied Logic 2 (2004) 245-272 Special Issue on Neural-Symbolic Systems.
Jacobsson, H.: Rule extraction from recurrent neural networks: A taxonomy and review. Neural Computation 17 (2005) 1223-1263
Setiono, R.: Extracting rules from neural networks by pruning and hidden-unit splitting. Neural Computation 9 (1997) 205-225
Sun, R.: Robust reasoning: integrating rule-based and similarity-based reason-ing. Artificial Intelligence 75 (1995) 241-296
d’Avila Garcez, A.S., Elman, J., Hitzler, P., eds.: Proceedings of IJCAI International Workshop on Neural-Symbolic Learning and Reasoning NeSy05, Edinburgh, Scotland (2005)
d’Avila Garcez, A.S., Hitzler, P., Tamburrini, G., eds.: Proceedings of ECAI International Workshop on Neural-Symbolic Learning and Reasoning NeSy06, Trento, Italy (2006)
Shastri, L.: Advances in SHRUTI: a neurally motivated model of relational knowledge representation and rapid inference using temporal synchrony. Applied Intelligence 11 (1999) 79-108
Hölldobler, S., Kalinke, Y.: Toward a new massively parallel computational model for logic programming. In: Proceedings of the Workshop on Combining Symbolic and Connectionist Processing, ECAI 94. (1994) 68-77
Towell, G.G., Shavlik, J.W.: Knowledge-based artificial neural networks. Arti-ficial Intelligence 70 (1994) 119-165
Thrun, S.B.: Extracting provably correct rules from artificial neural networks. Technical report, Institut fur Informatik, Universitat Bonn (1994)
Smolensky, P., Legendre, G.: The Harmonic Mind: From Neural Computation to Optimality-Theoretic Grammar. MIT Press, Cambridge, Mass (2006)
Page, M.: Connectionist modelling in psychology: A localist manifesto. Behavioral and Brain Sciences 23 (2000) 443-467
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representa-tions by error propagation. In Rumelhart, D.E., McClelland, J.L., eds.: Parallel Distributed Processing. Volume 1. MIT Press (1986) 318-362
Lloyd, J.W.: Foundations of Logic Programming. Springer-Verlag (1987)
Gelfond, M., Lifschitz, V.: Classical negation in logic programs and disjunctive databases. New Generation Computing 9 (1991) 365-385
d’Avila Garcez, A.S., Lamb, L.C.: Neural-symbolic systems and the case for non-classical reasoning. In Artemov, S., Barringer, H., d’Avila Garcez, A.S., Lamb, L.C., Woods, J., eds.: We will show them! Essays in Honour of Dov Gabbay. International Federation for Computational Logic, College Publications, London (2005) 469-488
Fagin, R., Halpern, J., Moses, Y., Vardi, M.: Reasoning about Knowledge. MIT Press (1995)
d’Avila Garcez, A.S., Gabbay, D.M., Lamb, L.C.: Value-based argumentation frameworks as neural-symbolic learning systems. Journal of Logic and Compu-tation 15 (2005) 1041-1058
d’Avila Garcez, A.S., Lamb, L.C., Broda, K., Gabbay, D.M.: Applying connectionist modal logics to distributed knowledge representation problems. International Journal on Artificial Intelligence Tools 13 (2004) 115-139
Vardi, M.: Why is modal logic so robustly decidable? In: Descriptive Complexity and Finite Models. DIMACS Series in Discrete Mathematics and Theoretical Computer Science, American Mathematical Society (1996) 149-184
Orgun, M.A., Ma, W.: An overview of temporal and modal logic programming. In: Proc. Inl. Conf. Temporal Logic. LNAI 827, Springer (1994) 445-479
Hölldobler, S., Kalinke, Y., Storr, H.P.: Approximating the semantics of logic programs by recurrent neural networks. Applied Intelligence 11 (1999) 45-58
Gabbay, D.M.: Fibring Logics. Oxford Univesity Press (1999)
Gabbay, D.M., Hunter, A.: Making inconsistency respectable: Part 2 - meta-level handling of inconsistency. In: Symbolic and Quantitative Approaches to Reasoning and Uncertainty ECSQARU’93. Volume LNCS 747., Springer-Verlag (1993)129-136
d’Avila Garcez, A.S., Lamb, L., Gabbay, D.M.: Connectionist Non-Classical Reasoning. Cognitive Technologies. Springer-Verlag (2007) to appear.
Muggleton, S., Raedt, L.: Inductive logic programming: theory and methods. Journal of Logic Programming 19 (1994) 629-679
Gabbay, D.M.: Elementary Logics: a Procedural Perspective. Prentice Hall, London (1998)
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
Garcez, A.S.d. (2007). Advances in Neural-Symbolic Learning Systems: Modal and Temporal Reasoning. 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_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-73954-8_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73953-1
Online ISBN: 978-3-540-73954-8
eBook Packages: EngineeringEngineering (R0)