The Strength of Weak Learnability

Machine Learning

Volumn 5, Issue 2, 1990, Pages 197-227

  Schapire, Robert E ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

learnability theory; learning from examples; Machine learning; PAC learning; polynomial time identification

Indexed keywords

MATHEMATICAL TECHNIQUES--ALGORITHMS;

DISTRIBUTION-FREE LEARNING MODELS; LEARNING ALGORITHMS; POLYNOMIALLY LEARNABLE CLASSES; STRONGLY LEARNABLE CONCEPT CLASSES; WEAKLY LEARNABLE CONCEPT CLASSES;

LEARNING SYSTEMS;

EID: 0025448521     PISSN: 08856125     EISSN: 15730565     Source Type: Journal    
DOI: 10.1023/A:1022648800760     Document Type: Article

References (25)

1. Finding patterns common to a set of strings
2. Queries and concept learning
3. Fast probabilistic algorithms for Hamiltonian circuits and matchings
4. Occam's razor
5. Learnability and the Vapnik-Chervonenkis dimension
6. On the necessity of Occam algorithms
7. Some remarks about space-complexity of learning, and circuit complexity of recognizing
8. Learning decision trees from random examples
9. Space-bounded learning and the Vapnik-Chervonenkis dimension
10. Equivalence of models for polynomial learnability
11. Predicting {0, 1}-functions on randomly drawn points
12. Learning nested differences of intersection-closed concept classes
13. Probability inequalities for sums of bounded random variables
14. On the learnability of Boolean formulae
15. Cryptographic limitations on learning Boolean formulae and finite automata
16. Computational limitations on learning from examples
17. Learning decision lists
18. A theory of the learnable