Weizmann Logo
ECCC
Electronic Colloquium on Computational Complexity

Under the auspices of the Computational Complexity Foundation (CCF)

Login | Register | Classic Style



REPORTS > DETAIL:

Paper:

TR97-052 | 11th November 1997 00:00

Analog Neural Nets with Gaussian or other Common Noise Distributions cannot Recognize Arbitrary Regular Languages

RSS-Feed




TR97-052
Authors: Eduardo D. Sontag
Publication: 11th November 1997 14:07
Downloads: 2220
Keywords: 


Abstract:

We consider recurrent analog neural nets where the output of each
gate is subject to Gaussian noise, or any other common noise
distribution that is nonzero on a large set.
We show that many regular languages cannot be recognized by
networks of this type, and
we give a precise characterization of those languages which can be
recognized. This result implies severe constraints on possibilities
for constructing recurrent analog neural nets that are robust
against realistic types of analog noise. On the other hand we
present a method for constructing feedforward analog neural nets
that are robust with regard to analog noise of this type.



ISSN 1433-8092 | Imprint