W. Maass et Ed. Sontag, Analog neural nets with gaussian or other common noise distributions cannot recognize arbitrary regular languages, NEURAL COMP, 11(3), 1999, pp. 771-782
Citations number
9
Categorie Soggetti
Neurosciences & Behavoir","AI Robotics and Automatic Control
We consider recurrent analog neural nets where the output of each gate is s
ubject to gaussian noise or any other common noise distribution that is non
zero on a sufficiently large part of the state-space. We show that many reg
ular languages cannot be recognized by networks of this type, and we give a
precise characterization of languages that can be recognized. This result
implies severe constraints on possibilities for constructing recurrent anal
og neural nets that are robust against realistic types of analog noise. On
the other hand, we present a method for constructing feedforward analog neu
ral nets that are robust with regard to analog noise of this type.