Learnability with respect to fixed distributions

Theoretical Computer Science

Volumn 86, Issue 2, 1991, Pages 377-389

  Benedek, Gyora M ^a   Itai, Alon ^a  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER METATHEORY - COMPUTATIONAL COMPLEXITY; COMPUTER PROGRAMMING - ALGORITHMS; PROBABILITY - RANDOM PROCESSES;

DISCRETE DISTRIBUTIONS; FINITE COVERS; LEARNABILITY; LEARNING ALGORITHMS;

LEARNING SYSTEMS;

EID: 0026414013     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/0304-3975(91)90026-X     Document Type: Article

References (17)

1. Learning from noisy examples
2. Fast probabilistic algorithms for Hamiltonian circuits and matchings
3. Nonuniform learnability
4. Learnability and the Vapnik-Chervonenkis dimension
5. Occam's razor
6. A general lower bound on the number of examples needed for learning
7. Equivalence of models for polynomial learnability
8. On the learnability of boolean formulae
9. On learning boolean functions
10. B.K. Natarajan, Probably-approximate learning over classes of distributions, unpublished manuscript.
11. Computational limitations on learning from examples
12. On the uniform convergence of relative frequencies of events to their probabilities
13. A theory of the learnable
14. Learning disjunctions of conjunctions
15. L.G. Valiant, Deductive learning, Philos. Trans. Roy. London Ser. A 312, 441–446.