On probabilistic analog automata

Authors:
Asa Ben-Hur;Alexander Roitershtein;Hava T. Siegelmann
Affiliations:
Department of Biochemistry, B400 Beckman Center, Stanford University, CA;Department of Mathematics, Technion - IIT, Haifa 32000, Israel;Department of Computer Science, University of Massachusetts at Amherst, 710 N. Pleasant Street Amherst, MA
Venue:
Theoretical Computer Science
Year:
2004

Citing 6
Cited 0

On the computational power of neural nets

Journal of Computer and System Sciences
On the effect of analog noise in discrete-time analog computations

Neural Computation
Analog neural nets with Gaussian or other common noise distributions cannot recognize arbitary regular languages

Neural Computation
Neural networks and analog computation: beyond the Turing limit

Neural networks and analog computation: beyond the Turing limit
Introduction to probabilistic automata (Computer science and applied mathematics)

Introduction to probabilistic automata (Computer science and applied mathematics)
The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction

Neural Computation

Quantified Score

Hi-index	5.23

Visualization

Abstract

We consider probabilistic automata on a general state space and study their computational power. The model is based on the concept of language recognition by probabilistic automata due to Rabin (Inform. Control 3 (1963) 230) and models of analog computation in a noisy environment suggested by Maass and Orponen (Neural Comput. 10 (1998) 1071), and Maass and Sontag (Neural Comput. 11 (1999) 771). Our main result is a generalization of Rabin's reduction theorem that implies that under very mild conditions, the computational power of such automata is limited to regular languages.