Abstract
We show how to use recursive function theory to prove Turing universality of finite analog recurrent neural nets, with a piecewise linear sigmoid function as activation function. We emphasize the modular construction of nets within nets, a relevant issue from the software engineering point of view.
This work was supported by JNICT PBIC/TIT/2527/95 and a fellowship from the Gobierno Autonomo de Canarias.
Preview
Unable to display preview. Download preview PDF.
References
BOOLOS, G. and JEFFREY, R., Computability and Logic, (2° Ed), Cambridge University Press, 1980.
H.SIEGELMANN and E.SONTAG, “Neural Nets are Universal Computing Devices”. SYCON Report 91-08, Rutgers University, 1991.
H.SIEGELMANN and E.SONTAG, “On the Computational Power of Neural Nets”, in Journal of Computer and System Science [50] 1, Academic Press, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Neto, J.P., Siegelmann, H.T., Costa, J.F., Araujo, C.P.S. (1997). Turing universality of neural nets (revisited). In: Pichler, F., Moreno-Díaz, R. (eds) Computer Aided Systems Theory — EUROCAST'97. EUROCAST 1997. Lecture Notes in Computer Science, vol 1333. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0025058
Download citation
DOI: https://doi.org/10.1007/BFb0025058
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63811-7
Online ISBN: 978-3-540-69651-3
eBook Packages: Springer Book Archive