Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

7

COLT
2004
Springer

favoriteEmaildiscussreport

99views Machine Learning» more COLT 2004»

Learning Classes of Probabilistic Automata

13 years 10 months ago

Learning Classes of Probabilistic Automata

Download www.cmi.univ-mrs.fr

Abstract. Probabilistic ﬁnite automata (PFA) model stochastic languages, i.e. probability distributions over strings. Inferring PFA from stochastic data is an open ﬁeld of research. We show that PFA are identiﬁable in the limit with probability one. Multiplicity automata (MA) is another device to represent stochastic languages. We show that a MA may generate a stochastic language that cannot be generated by a PFA, but we show also that it is undecidable whether a MA generates a stochastic language. Finally, we propose a learning algorithm for a subclass of PFA, called PRFA.

François Denis, Yann Esposito

Real-time Traffic

COLT 2004 | Model Stochastic Languages | Probabilistic ﬁnite Automata | Stochastic Language |

claim paper

Related Content

» Learnability of Probabilistic Automata via Oracles

» A Class of Probabilistic Automata with a Decidable Value 1 Problem

» A Spectral Approach for Probabilistic Grammatical Inference on Trees

» Open Synchronous Cellular Learning Automata

» Learning Rational Stochastic Languages

» Derandomization of Probabilistic Auxiliary Pushdown Automata Classes

» Grammatical inference as a principal component analysis problem

» Uncountable Automatic Classes and Learning

» Performance Analysis of Probabilistic Timed Automata Using Digital Clocks

Post Info
More Details (n/a)

Added	01 Jul 2010
Updated	01 Jul 2010
Type	Conference
Year	2004
Where	COLT
Authors	François Denis, Yann Esposito

Comments (0)