Learning regular languages from simple positive examples

Machine Learning

Volumn 44, Issue 1-2, 2001, Pages 37-66

  Denis, François ^a  

^a UNIV LILLE   (France)

Author keywords

Deterministic finite automata; Grammatical inference; Kolmogorov complexity; PAC learning; Regular languages

Indexed keywords

DATA ACQUISITION; FINITE AUTOMATA; FORMAL LANGUAGES; HEURISTIC METHODS; MATHEMATICAL MODELS;

GRAMAMTICAL INFERENCES; KOLMOGOROV COMPLEXITIES;

LEARNING SYSTEMS;

EID: 0035399494     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1010826628977     Document Type: Article

References (36)

1. Inductive inference of formal languages from positive data
2. Inference of reversible languages
3. Learning regular sets from queries and counterexamples
4. Learning stochastic regular grammars by means of a state merging method
5. Angluin's theorem for indexed families of r.e. sets and applications
6. PAC learning from positive statistical queries
7. PAC learning with simple examples
8. PAC learning under helpful distributions
9. Language identification in the limit
10. Complexity of automaton identification from given data
11. Teaching a smarter learner
12. Equivalence of models for polynomial learnability
13. Locality, reversibility and beyond: Learning languages from positive data
14. Characteristic sets for polynomial grammatical inference
15. Identification in the limit of categorial grammars
16. Cryptographic limitations on learning boolean formulae and finite automata
17. Learning deterministic even linear languages from positive examples
18. Learning simple concepts under simple distributions
19. Text and monographs in computer science
20. Probably approximate learning of sets and functions
21. Inferring regular languages in polynomial update time
22. Learning DFA from simple examples
23. Inductive inference, DFAs, and computational complexity
24. An introduction to hidden markov models
25. Efficient learning of context-free grammars from positive structural examples
26. Recent advances of grammatical inference
27. A necessary condition for learning from positive examples
28. Inducing probabilistic grammars by Bayesian model merging
29. Meaning helps learning syntax
30. A theory of the learnable
31. On polynomial-time learnability in the limit of strictly deterministic automata