Linear concepts and hidden variables: An empirical study

Advances in Neural Information Processing Systems

Volumn , Issue , 1998, Pages 500-506

  Grove, Adam J ^a   Roth, Dan ^b  

^a NEC LABORATORIES AMERICA   (United States)

^b University of Illinois at Urbana Champaign   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CLASSIFICATION TASKS; EMPIRICAL STUDIES; HIDDEN VARIABLE; LEARNING TECHNIQUES; LINEAR CLASSIFIERS; LINEAR FUNCTIONS; OBSERVED VALUES; PROBABILISTIC MODELING;

ALGORITHMS;

EID: 84898974674     PISSN: 10495258     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. [Blu97] A. Blum. Empirical support for winnow and weighted majority based algorithms: results on a calendar scheduling domain. Machine Learning, 26:1-19, 1997.
2. [DLR77] A. P. Dempster, N. M. Laird, and D. B. Rubin. Maximum likelihood from incomplete data via the EM algorithm. Royal Statistical Society By 39:1-38, 1977.
3. [GR96] A. R. Golding and D. Roth. Applying winnow to context-sensitive spelling correcton. In Proc. 13th International Conference on Machine Learning (ML'96), pages 182-190, 1996.
4. [HS92] K. Httffgen and H. Simon. Robust trainability of single neurons. In Proc. 5th Annu. Workshop on Comput. Learning Theory, pages 428-439, New York, New York, 1992. ACM Press.
5. [Lit88] N. Littlestone. Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285-318, 1988.
6. [Lit91] N. Littlestone. Redundant noisy attributes, attribute errors, and linear threshold learning using Winnow. In Proc. 4th Annu. Workshop on Comput. Learning Theory, pages 147-156, San Mateo, CA, 1991. Morgan Kaufmann.
7. [MP69] M. L. Minsky and S. A. Papert. Perceptrons. MIT Press, Cambridge, MA, 1969.