Abstract
A concept of accepting colonies is introduced. A hybrid connectionist-symbolic architecture (“neural pushdown automaton”) for inference of colonies based on presentation of positive and negative examples of strings is then described, together with an algorithm for extracting a colony from trained neural network. Some examples of the inference of colonies generating/accepting simple context-free languages illustrate the function of the architecture.
Research supported by the Grant Agency of Czech Republic, grant No. 201/95/0134.
Preview
Unable to display preview. Download preview PDF.
References
R. Alquézar, A. Sanfeliu: An algebraic framework to represent finite state machines in single-layer recurrent neural networks. Neural Computation, No. 7, 931–949 (1995).
R. Alquézar, A. Sanfeliu, J. Cueva: Learning of context-sensitive language acceptors through regular inference and constraint induction. In: Proc. ICGI'96, L.Miclet and C.de la Higuera (eds.), Springer-Verlag, Lecture Notes in Artificial Intelligence 1147, 134–145, 1996.
H. Bordihn, H. Fernau: Accepting grammars and systems. TR 9/94, Universität Karlsruhe, Fakultät für Informatik 1994.
H. Fernau, H. Bordihn: Remarks on accepting parallel systems. Intern. J. Computer Math., vol. 56, 51–67.
H. Fernau, M. Holzer, H. Bordihn: Accepting multi-agent systems: the case of cooperating distributed grammar systems. Computers and Artificial Intelligence, vol. 15 (1996), No. 2–3, 123–139.
C. Giles, C. Omlin: Extraction, insertion and refinement of symbolic rules in dynamically-driven recurrent neural networks. In: [21], p.307.
M. Goudreau, C. Giles, S. Chakradhar, D. Chen: First-order vs. second-order single layer recurrent neural networks. In: IEEE Trans. on Neural Networks, vol. 5, no. 3, p. 511, 1994.
J. Hertz et.al.: Introduction to the Theory of Neural Computation. Addison-Wesley 1991.
J. Hořejš: A view on neural network paradigms development. Neural Network World, IDG Prague, 1991,1992.
J. Kelemen, A. Kelemenová: A grammar-theoretic treatment of multiagent systems. Cybernet. Systems 23 (1992), 621–633.
A. Kelemenová, E. Csuhaj-Varjú: Languages of colonies. Theoretical Computer Science, 134, Elsevier 1994, 119–130.
A. Kelemenová, J. Kelemen: From Colonies to Eco(grammar)systems: An Overview. In: Results and Trends in Theoretical Computer Science 812, (eds.) J.Karhumäki, H.Maurer, G.Rozenberg, Springer Verlag, Berlin, 1994, 213–231.
S. C. Kleene: Representation of events in nerve nets and finite automata. In: C. E. Shannon, J. McCarthy (eds.): Automata Studies, 3–41, Princeton Univ. Press 1956.
M. Mozer, S.Das: A connectionist symbol manipulator that discover the structure of context-free languages. Advances in Neural Information Processing Systems, vol. 5 (1993), S. Hanson, J. Cowan, C. Gilles (eds.), Morgan Kaufmann, p.863.
Gh. Păun (ed.): Artificial Life: Grammatical Models. The Black Sea University Press, Bucharest, 1995.
Gh. Păun, L. Sântean: Parallel communicating grammar systems: the regular case, Ann. Univ. Buc., Math.-Informatics Series 38 (1989) 55–63.
J. Pollack: Recursive ditribute representation. Journal of Artificial Intelligence, vol. 46 (1990), 77–105.
H. Siegelmann, E. D. Sontag: On the computational power of neural nets. In: Proc. Fifth ACM Workshop on Computational Learning Theory, 440–449, Pittsburgh 1992.
P. Sosík: Eco-grammar systems and artificial neural networks. Computers and Artificial Intelligence, No. 2–3 (1996), 247–264.
P. Sosík: On hybrid connectionist-symbolic models. Acta Cybernetica, accepted, 1997.
Special issue on architectures for integrating symbolic and neural processes. Connection Science, vol. 5, No. 3–4, 1993.
G. Sun, C. Giles, H. Chen, Y. Lee: The neural network pushdown automaton: model, stack and learning simulations. Univerzity of Maryland TR Nos. UMIACS-TR-93-77 & CS-TR-3118, 1995.
D. Wood: Theory of Computation. John Wiley & Sons 1987.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Sosík, P., Štýbnar, L. (1997). Grammatical inference of colonies. In: Păun, G., Salomaa, A. (eds) New Trends in Formal Languages. Lecture Notes in Computer Science, vol 1218. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62844-4_16
Download citation
DOI: https://doi.org/10.1007/3-540-62844-4_16
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62844-6
Online ISBN: 978-3-540-68703-0
eBook Packages: Springer Book Archive