Learning Probabilistic Residual Finite State Automata

Authors:
Yann Esposito;Aurélien Lemay;François Denis;Pierre Dupont
Affiliations:
-;-;-;-
Venue:
ICGI '02 Proceedings of the 6th International Colloquium on Grammatical Inference: Algorithms and Applications
Year:
2002

Citing 7
Cited 5

Results of the Abbadingo One DFA Learning Competition and a New Evidence-Driven State Merging Algorithm

ICGI '98 Proceedings of the 4th International Colloquium on Grammatical Inference
Learning Regular Languages Using Non Deterministic Finite Automata

ICGI '00 Proceedings of the 5th International Colloquium on Grammatical Inference: Algorithms and Applications
Probabilistic DFA Inference using Kullback-Leibler Divergence and Minimality

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Learning Stochastic Regular Grammars by Means of a State Merging Method

ICGI '94 Proceedings of the Second International Colloquium on Grammatical Inference and Applications
Inducing Probabilistic Grammars by Bayesian Model Merging

ICGI '94 Proceedings of the Second International Colloquium on Grammatical Inference and Applications
Residual Finite State Automata

STACS '01 Proceedings of the 18th Annual Symposium on Theoretical Aspects of Computer Science
Learning Regular Languages Using RFSA

ALT '01 Proceedings of the 12th International Conference on Algorithmic Learning Theory

PAC-learnability of Probabilistic Deterministic Finite State Automata

The Journal of Machine Learning Research
On Rational Stochastic Languages

Fundamenta Informaticae
Links between probabilistic automata and hidden Markov models: probability distributions, learning models and induction algorithms

Pattern Recognition
Residual languages and probabilistic automata

ICALP'03 Proceedings of the 30th international conference on Automata, languages and programming
On Rational Stochastic Languages

Fundamenta Informaticae

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a new class of probabilistic automata: Probabilistic Residual Finite State Automata. We show that this class can be characterized by a simple intrinsic property of the stochastic languages they generate (the set of residual languages is finitely generated by residuals) and that it admits canonical minimal forms. We prove that there are more languages generated by PRFA than by Probabilistic Deterministic Finite Automata (PDFA). We present a first inference algorithm using this representation and we show that stochastic languages represented by PRFA can be identified from a characteristic sample if words are provided with their probabilities of appearance in the target language.