Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/73316
Title: Turing universality of neural nets (revisited)
Authors: Neto, Pedro J.
Siegelmann, Hava T.
Costa, Félix J.
Suárez Araujo, C. P. 
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: Modularity
Neural computation
Recursive function theory
Issue Date: 1997
Journal: Lecture Notes in Computer Science 
Conference: 6th International Workshop on Computer Aided Systems Theory, EUROCAST 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.
URI: http://hdl.handle.net/10553/73316
ISBN: 3-540-63811-3
ISSN: 0302-9743
DOI: 10.1007/BFb0025058
Source: Pichler F., Moreno-Díaz R. (eds) Computer Aided Systems Theory — EUROCAST 1997. Lecture Notes in Computer Science, v. 1333, p. 361-366. Springer, Berlin, Heidelberg [ISSN 0302-9743], (Enero 1997)
Appears in Collections:Actas de congresos
Show full item record

SCOPUSTM   
Citations

10
checked on Aug 1, 2021

Page view(s)

33
checked on Jul 31, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.