PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Learning Stochastic Deterministic Regular Languages
Franck Thollard and Alexander Clark
In: ICGI 2004, 11 - 13 October 2004, Athen, Greece.

Abstract

We propose in this article a new practical algorithm for inferring $\mu$-distinguishable stochastic deterministic regular languages. We prove that this algorithm will infer, with high probability, an automaton isomorphic to the target when given a polynomial number of examples. We discuss the links between the error function used to evaluate the inferred model and the learnability of the model class in a PAC like framework.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
Postscript - Requires a viewer, such as GhostView
EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:419
Deposited By:Franck Thollard
Deposited On:19 December 2004