INTERACTIVE EVOLVING RECURRENT NEURAL NETWORKS ARE SUPER-TURING

Jérémie Cabessa

Abstract

We consider a model of evolving recurrent neural networks where the synaptic weights can change over time, and we study the computational power of such networks in a basic context of interactive computation. In this framework, we prove that both models of rational- and real-weighted interactive evolving neural networks are computationally equivalent to interactive Turing machines with advice, and hence capable of super-Turing capabilities. These results support the idea that some intrinsic feature of biological intelligence might be beyond the scope of the current state of artificial intelligence, and that the concept of evolution might be strongly involved in the computational capabilities of biological neural networks. It also shows that the computational power of interactive evolving neural networks is by no means influenced by nature of their synaptic weights.

References

  1. Cabessa, J. and Siegelmann, H. T. (2011a). The computational power of interactive recurrent neural networks. Submitted to Neural Comput.
  2. Cabessa, J. and Siegelmann, H. T. (2011b). Evolving recurrent neural networks are super-Turing. In International Joint Conference on Neural Networks, IJCNN 2011, pages 3200-3206. IEEE.
  3. Goldin, D., Smolka, S. A., and Wegner, P. (2006). Interactive Computation: The New Paradigm. SpringerVerlag New York, Inc., Secaucus, NJ, USA.
  4. Kleene, S. C. (1956). Representation of events in nerve nets and finite automata. In Automata Studies, volume 34 of Annals of Mathematics Studies. Princeton University Press, Princeton, NJ, USA.
  5. McCulloch, W. S. and Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysic, 5:115-133.
  6. Minsky, M. L. (1967). Computation: finite and infinite machines. Prentice-Hall, Inc., Upper Saddle River, NJ, USA.
  7. Siegelmann, H. T. (1999). Neural networks and analog computation: beyond the Turing limit. Birkhauser Boston Inc., Cambridge, MA, USA.
  8. Siegelmann, H. T. and Sontag, E. D. (1994). Analog computation via neural networks. Theor. Comput. Sci., 131(2):331-360.
  9. Siegelmann, H. T. and Sontag, E. D. (1995). On the computational power of neural nets. J. Comput. Syst. Sci., 50(1):132-150.
  10. van Leeuwen, J. and Wiedermann, J. (2001a). Beyond the Turing limit: Evolving interactive systems. In SOFSEM 2001: Theory and Practice of Informatics, volume 2234 of LNCS, pages 90-109. Springer Berlin / Heidelberg.
  11. van Leeuwen, J. and Wiedermann, J. (2001b). The Turing machine paradigm in contemporary computing. In Mathematics Unlimited - 2001 and Beyond, LNCS, pages 1139-1155. Springer-Verlag.
  12. van Leeuwen, J. and Wiedermann, J. (2008). How we think of computing today. In Logic and Theory of Algorithms, volume 5028 of LNCS, pages 579-593. Springer Berlin / Heidelberg.
  13. Wegner, P. (1998). Interactive foundations of computing. Theor. Comput. Sci., 192:315-351.
Download


Paper Citation


in Harvard Style

Cabessa J. (2012). INTERACTIVE EVOLVING RECURRENT NEURAL NETWORKS ARE SUPER-TURING . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-8425-95-9, pages 328-333. DOI: 10.5220/0003740603280333


in Bibtex Style

@conference{icaart12,
author={Jérémie Cabessa},
title={INTERACTIVE EVOLVING RECURRENT NEURAL NETWORKS ARE SUPER-TURING},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2012},
pages={328-333},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003740603280333},
isbn={978-989-8425-95-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - INTERACTIVE EVOLVING RECURRENT NEURAL NETWORKS ARE SUPER-TURING
SN - 978-989-8425-95-9
AU - Cabessa J.
PY - 2012
SP - 328
EP - 333
DO - 10.5220/0003740603280333