Turing universality of neural nets (revisited)
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.
KeywordsNeural computation recursive function theory modularity
Unable to display preview. Download preview PDF.
- [Boolos 80]BOOLOS, G. and JEFFREY, R., Computability and Logic, (2° Ed), Cambridge University Press, 1980.Google Scholar
- [Siegelmann and Sontag 91]H.SIEGELMANN and E.SONTAG, “Neural Nets are Universal Computing Devices”. SYCON Report 91-08, Rutgers University, 1991.Google Scholar
- [Siegelmann and Sontag 95]H.SIEGELMANN and E.SONTAG, “On the Computational Power of Neural Nets”, in Journal of Computer and System Science  1, Academic Press, 1995.Google Scholar