Recurrent Neural Networks - A Natural Model of Computation beyond the Turing Limits
Jérémie Cabessa, Alessandro E. P. Villa
2012
Abstract
According to the Church-Turing Thesis, the classical Turing machine model is capable of capturing all possible aspects of algorithmic computation. However, in neural computation, several basic neural models were proven to be capable of computational capabilities located beyond the Turing limits. In this context, we present an overview of recent results concerning the super-Turing computational power of recurrent neural networks, and show that recurrent neural networks provide a suitable and natural model of computation beyond the Turing limits. We nevertheless don’t draw any hasty conclusion about the controversial issue of a possible predominance of biological intelligence over the potentialities of artificial intelligence.
DownloadPaper Citation
in Harvard Style
Cabessa J. and E. P. Villa A. (2012). Recurrent Neural Networks - A Natural Model of Computation beyond the Turing Limits . In Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012) ISBN 978-989-8565-33-4, pages 594-599. DOI: 10.5220/0004172905940599
in Bibtex Style
@conference{ncta12,
author={Jérémie Cabessa and Alessandro E. P. Villa},
title={Recurrent Neural Networks - A Natural Model of Computation beyond the Turing Limits},
booktitle={Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012)},
year={2012},
pages={594-599},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004172905940599},
isbn={978-989-8565-33-4},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: NCTA, (IJCCI 2012)
TI - Recurrent Neural Networks - A Natural Model of Computation beyond the Turing Limits
SN - 978-989-8565-33-4
AU - Cabessa J.
AU - E. P. Villa A.
PY - 2012
SP - 594
EP - 599
DO - 10.5220/0004172905940599