Stochastic finite learning of the pattern languages

Machine Learning

Volumn 44, Issue 1-2, 2001, Pages 67-91

  Rossmanith, Peter ^a   Zeugmann, Thomas ^b  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

^b UNIVERSITY OF LÜBECK   (Germany)

Author keywords

Average case analysis; Inductive learning; Learning in the limit; Pattern languages; Stochastic finite learning

Indexed keywords

FORMAL LANGUAGES; LEARNING ALGORITHMS; MATHEMATICAL MODELS; PROBABILITY DISTRIBUTIONS; RANDOM PROCESSES;

PATTERN LANGUAGES; STOCHASTIC FINITE LEARNING;

LEARNING SYSTEMS;

EID: 0035399492     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1010875913047     Document Type: Article

References (28)

1. Finding patterns common to a set of strings
2. Inductive inference of formal languages from positive data
3. Learnability and the Vapnik-Chervonenkis dimension
4. On the complexity of inductive inference
5. Learning one-variable pattern languages very efficiently on average, in parallel, and by asking queries
6. Prudence and other conditions on formal language learning
7. Language identification in the limit
8. Exact identification of circuits using fixed points of amplification functions
9. A guided tour of Chernoff bounds
10. Equivalence of models for polynomial learnability
11. A polynomial-time algorithm for learning k-variable pattern languages from examples
12. Polynomial-time inference of arbitrary pattern languages
13. Monotonic versus non-monotonic language learning
14. Set-driven and rearrangement-independent learning of recursive languages
15. The VC-dimension of subclasses of pattern languages
16. Bayesian inductive logic programming
17. Inductive inference, DFAs and computational complexity
18. Learning one-variable pattern languages in linear average time
19. A complete and tight average-case analysis of learning monomials
20. Learning k-variable pattern languages efficiently stochastically finite on average from positive data
21. Patterns. (The formal language theory column)
22. Return to patterns. (The formal language theory column)
23. Pattern languages are not learnable
24. Pattern inference
25. A theory of the learnable
26. Lange and Wiehagen's pattern learning algorithm: An average-case analysis with respect to its total learning time
27. A guided tour across the boundaries of learning recursive languages