Connectionist modal logic: Representing modalities in neural networks

Theoretical Computer Science

Volumn 371, Issue 1-2, 2007, Pages 34-53

  d'Avila Garcez, Artur S ^a   Lamb, Luís C ^b   Gabbay, Dov M ^c  

^a CITY UNIVERSITY   (United Kingdom)

^b FEDERAL UNIVERSITY OF RIO GRANDE DO SUL   (Brazil)

^c KING'S COLLEGE LONDON   (United Kingdom)

Author keywords

Artificial neural networks; Knowledge representation; Modal logics; Models of computation; Neural symbolic learning systems

Indexed keywords

COMPUTATION THEORY; COMPUTER SCIENCE; KNOWLEDGE REPRESENTATION; LEARNING SYSTEMS; MATHEMATICAL MODELS; NEURAL NETWORKS; PROBLEM SOLVING;

MODAL LOGICS; MODELS OF COMPUTATION; NEURAL-SYMBOLIC LEARNING SYSTEMS; NEUROCOMPUTING;

FORMAL LOGIC;

EID: 33846781326     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.tcs.2006.10.023     Document Type: Article

References (45)

1. V. Ajjanagadde, Rule-Based Reasoning in Connectionist Networks, Ph.D. Thesis, University of Minnesota, 1997
2. Baldoni M., Giordano L., and Martelli A. A modal extension of logic programming: Modularity, beliefs and hypothetical reasoning. Journal of Logic and Computation 8 5 (1998) 597-635
3. Bose N.K., and Liang P. Neural Networks Fundamentals with Graphs, Algorithms, and Applications (1996), McGraw-Hill
4. Brewka G., and Eiter T. Preferred answer sets for extended logic programs. Artificial Intelligence 109 (1999) 297-356
5. Broda K., Gabbay D.M., Lamb L.C., and Russo A. Labelled natural deduction for conditional logics of normality. Logic Journal of the IGPL 10 2 (2002) 123-163
6. Broda K., Gabbay D.M., Lamb L.C., and Russo A. Compiled Labelled Deductive Systems: A Uniform Presentation of Non-Classical Logics (2004), Research Studies Press, Institute of Physics Publishing
7. Castilho M.A., Farinas del Cerro L., Gasquet O., and Herzig A. Modal tableaux with propagation rules and structural rules. Fundamenta Informaticae 32 (1997) 281-297
8. Chagrov A., and Zakharyaschev M. Modal Logic (1997), Clarendon Press, Oxford
9. Clark K.L. Negation as failure. In: Gallaire H., and Minker J. (Eds). Logic and Databases (1978), Plenum Press, New York 293-322
10. In: Cloete I., and Zurada J.M. (Eds). Knowledge-Based Neurocomputing (2000), The MIT Press
11. Cybenco G. Approximation by superposition of sigmoidal functions. Mathematics of Control, Signals and Systems vol. 2 (1989) 303-314
12. A.S. d'Avila Garcez, Extended theory refinement in knowledge-based neural networks, in: Proceedings of IEEE International Joint Conference on Neural Networks, IJCNN'02, Honolulu, Hawaii, 2002
13. d'Avila Garcez A.S. Fewer epistemological challenges for connectionism. In: Cooper S.B., Lowe B., and Torenvliet L. (Eds). Proceedings of Computability in Europe. CiE 2005. LNCS vol. 3526 (June 2005), Springer-Verlag, Amsterdam, The Netherlands 139-149
14. d'Avila Garcez A.S., Broda K., and Gabbay D.M. Symbolic knowledge extraction from trained neural networks: A sound approach. Artificial Intelligence 125 (2001) 155-207
15. d'Avila Garcez A.S., Broda K., and Gabbay D.M. Neural-Symbolic Learning Systems: Foundations and Applications. Perspectives in Neural Computing (2002), Springer-Verlag
16. d'Avila Garcez A.S., and Lamb L.C. Reasoning about time and knowledge in neural-symbolic learning systems. In: Thrun S., Saul L., and Schoelkopf B. (Eds). Proceedings of NIPS 2003. Advances in Neural Information Processing Systems vol. 16 (2004), MIT Press, Vancouver, Canada 921-928
17. d'Avila Garcez A.S., and 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., and Woods J. (Eds). We Will Show Them! Essays in Honour of Dov Gabbay (2005), International Federation for Computational Logic, College Publications, London 469-488
18. d'Avila Garcez A.S., and Zaverucha G. The connectionist inductive learning and logic programming system. Applied Intelligence 11 1 (1999) 59-77
19. Fagin R., Halpern J., Moses Y., and Vardi M. Reasoning about Knowledge (1995), MIT Press
20. Fitting M. Proof Methods for Modal and Intuitionistic Logics (1983), Reidel, Dordrecht
21. Fitting M. Metric methods: Three examples and a theorem. Journal of Logic Programming 21 (1994) 113-127
22. Gabbay D.M. Labelled Deductive Systems vol. 1 (1996), Clarendom Press, Oxford
23. Gabbay D.M., Hodkinson I., and Reynolds M. Temporal Logic: Mathematical Foundations and Computational Aspects (1994), Oxford University Press
24. Gelfond M., and Lifschitz V. Classical negation in logic programs and disjunctive databases. New Generation Computing 9 (1991) 365-385
25. Harel D. Dynamic logic. In: Gabbay D.M., and Guenthner F. (Eds). Handbook of Philosophical Logic vol. 2 (1984), D. Reidel, Boston 497-604
26. Haykin S. Neural Networks: A Comprehensive Foundation (1999), Prentice Hall
27. S. Holldobler, Y. Kalinke, Toward a new massively parallel computational model for logic programming, in: Proceedings of the Workshop on Combining Symbolic and Connectionist Processing, ECAI 94, 1994, pp. 68-77
28. G.E. Hughes, M.J. Cresswell, A New Introduction to Modal Logic, Routledge, London, New York, 1996
29. Huth M.R.A., and Ryan M.D. Logic in Computer Science: Modelling and Reasoning about Systems (2000), Cambridge Univ. Press
30. Lewis C. A Survey of Symbolic Logic (1918), University of California Press, Berkeley
31. Lloyd J.W. Foundations of Logic Programming (1987), Springer-Verlag
32. Mitchell T.M. Machine Learning (1997), McGraw-Hill
33. Orgun M.A., and Ma W. An overview of temporal and modal logic programming. Proc. Inl. Conf. Temporal Logic. LNAI vol. 827 (1994), Springer 445-479
34. Rumelhart D.E., Hinton G.E., and Williams R.J. Learning internal representations by error propagation. In: Rumelhart D.E., and McClelland J.L. (Eds). Parallel Distributed Processing vol. 1 (1986), MIT Press 318-362
35. Sakakibara Y. Programming in modal logic: An extension of PROLOG based on modal logic. Logic Programming 86. LNCS vol. 264 (1986), Springer 81-91
36. 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
37. Sun R. Robust reasoning: Integrating rule-based and similarity-based reasoning. Artificial Intelligence 75 2 (1995) 241-296
38. Sun R., and Alexandre F. Connectionist Symbolic Integration (1997), Lawrence Erlbaum Associates
39. S.B. Thrun, J. Bala, E. Bloedorn, I. Bratko, B. Cestnik, J. Cheng, K. De Jong, S. Dzeroski, S.E. Fahlman, D. Fisher, R. Haumann, K. Kaufman, S. Keller, I. Kononenko, J. Kreuziger, R.S. Michalski, T. Mitchell, P. Pachowicz, Y. Reich, H. Vafaie, K. Van de Welde, W. Wenzel, J. Wnek, J. Zhang, The MONK's problems: A performance comparison of different learning algorithms, Technical Report CMU-CS-91-197, Carnegie Mellon University, 1991
40. Towell G.G., and Shavlik J.W. Knowledge-based artificial neural networks. Artificial Intelligence 70 1 (1994) 119-165
41. Valiant L.G. Three problems in computer science. Journal of the ACM 50 1 (2003) 96-99
42. van Benthem J. Modal Logic and Classical Logic (1983), Bibliopolis, Napoli
43. van Benthem J. Correspondence theory. In: Gabbay D.M., and Guenthner F. (Eds). Handbook of Philosophical Logic (1984), D. Reidel Publishing Company, Dordrecht 167-247 (Chapter II.4)
44. M.Y. Vardi, Why is modal logic so robustly decidable, in: N. Immerman, P. Kolaitis (Eds.), Descriptive Complexity and Finite Models, in: Discrete Mathematics and Theoretical Computer Science, vol. 31, DIMACS, 1997, pp. 149-184
45. Zhou Z.H., Jiang Y., and Chen S.F. Extracting symbolic rules from trained neural network ensembles. AI Communications 16 1 (2003) 3-15