Boosting a weak learning algorithm by majority

Proceedings of the 3rd Annual Workshop on Computational Learning Theory, COLT 1990

Volumn , Issue , 1990, Pages 202-216

  Freund, Yoav ^a  

^a NONE

Author keywords

[No Author keywords available]

Indexed keywords

EID: 85043515682     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1016/b978-1-55860-146-8.50019-9     Document Type: Conference Paper

References (11)

1. Robert E. Schapire The Strength of Weak Learnability Symposium on Foundations of Computer Science 1989, 28–33.
2. Blumer Ehrenfeucht Haussler Warmuth Occam's Razor Information Processing letters 24 1987 North-Holland 377 380
3. Haussler, Kearns, Littlestone & Warmuth Equivalence for models of polynomial learnability proceeding of the 1988 Workshop on Computational Learning Theory , pages 42–55, Morgan-Kaufmann, Cambridge, MA, August 1988.
4. Blumer, Ehrenfeucht, Haussler & Warmuth Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension. Proc. 18th ACM Symp. on Theory of Computation , Berkeley, CA., 1986, 343–370.
5. Kearns & Valiant Cryptographic limitations on learning formulae and finite automata. In Proceedings of the Twenty-First Annual ACM Symposium on Theory of Computing , pages 433–444, Seattle, Washington, May 1989.
6. Kearns Valiant Learning Boolean Formulae or Finite Automata is as hard as Factoring 1988 Harvard University, Aiken Computation Laboratory Technical Report TR 14–88
7. B. Bollobas Random Graphs 1985 Academic Press 11
8. Learnability and the Vapnik-Chervonenkis dimension. Blumer, Ehrenfeucht, Haussler & Warmuth. Journal of the ACM, Vol 36, no 4, October 1989 pp. 929–965.
9. Board & Pitt On the Necessity of Occam Algorithms. In Proceedings of the Twenty-Second Annual ACM Symposium on Theory of Computing , pages 54–63, Baltimore, Maryland, May 1990.
10. Robert Schapire personal correspondence, may 1990.
11. Nick Littlestone & Manfred Warmuth Relating Data Compression and Learnability. 1987. (unpublished manuscript)