Presentation
Turing Universality of Neural Nets (revisited)
Proceedings of the Sixth International Conference on Computer Aided Systems Technology (EUROCAST'97)
(1997)
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.
Keywords
- Neural computation,
- recursive function theory,
- modularity
Disciplines
Publication Date
February, 1997
Citation Information
J. Pedro Neto, Hava Siegelmann, J. Félix Costa and C. P. Suárez Araujo. "Turing Universality of Neural Nets (revisited)" Proceedings of the Sixth International Conference on Computer Aided Systems Technology (EUROCAST'97) (1997) Available at: http://works.bepress.com/hava_siegelmann/18/