Learning Distributions by Their Density Levels: A Paradigm for Learning without a Teacher

Journal of Computer and System Sciences

Volumn 55, Issue 1, 1997, Pages 171-182

  Ben David, Shai ^a   Lindenbaum, Michael ^a  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER VISION; LEARNING ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; PATTERN RECOGNITION;

HIGH-DENSITY AREAS;

COMPUTER SCIENCE;

EID: 0031208638     PISSN: 00220000     EISSN: None     Source Type: Journal    
DOI: 10.1006/jcss.1997.1507     Document Type: Article

References (20)

1. D. Angluin and P. Laird, Learning from noisy examples, Machine Learning 2, No. 4 (1988), 343-370.
2. G. M. Benedek and A. Itai, Learnability with respect to fixed distributions, Theoret. Comput. Sci. 86 (1991), 377-389.
3. S. Ben-David and M. Lindebaum, Localization vs identification of semi-algebraic sets, in "Proc. 6th COLT, 1993," pp. 327-336.
4. A. Blumer, A. Ehrenfeucht, D. Haussler, and M. K. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, Assoc. Comput. Machine 36, No. 4 (1989), 929-965.
5. R. Canetti, G. Even, and O. Goldreich, Lower bounds for sampling algorithms for estimating the average, Computer Science Tech. Rep. 789, Technion-Israel Institute of Technology, 1993.
6. E. Dichterman, Private communication.
7. R. O. Duda and P. E. Hart, "Pattern Classification and Scene Analysis," Wiley, New York, 1973.
8. R. M. Dudley, "A Course on Empirical Processes," Lecture Notes in Mathematics, Vol. 1097, pp. 2-142, Springer-Verlag, New York/Berlin, 1984.
9. A. Ehrenfeucht, D. Haussler, M. Kearns, and L. Valiant, A general lower bound on the number of examples needed for learning, Inform. and Comput. 82, No. 3 (1989), 247-261.
10. P. Goldberg and M. Jerrum, Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers, Machine Learning 18 (1995), 131-148.
11. J. Illingworth and J. Kittler, A survey of Hough transform, Comput. Vision, Graphics, and Image Process. 44 (1988), 87-116.
12. M. Karpinski and A. MacIntyre, Polynomial bounds for VC-dimension of sigmoidal neural networks, in "Proceedings of 27th STOC, 1995," pp. 200-208.
13. A. G. Khovanskii, Fewnomials, Transi. Math. Monographs 88 (1981).
14. M. Kearns, Y. Mansour, D. Ron, R. Rubinfeld, R. E. Shapire, and L. Sellie, On the learnability of discrete distributions, in "Proceedings of 26th ACM STOC, 1994," pp. 273-282.
15. M. Kearns and R. E. Shapire, Efficient distribution-free learning of probabilistic concepts, in "Proc. of 31st FOCS, 1994," pp. 382-392; full version, J. Comput. System Sci., to appear.
16. M. W. Kim, Learning by smoothing: A morphological approach, in "Proc. of 4th COLT, 1991," pp. 43-57.
17. B. K. Natarajan, Probably approximate learning of sets and functions, SIAM J. Comput. 20, No. 1 (1991), 328-351.
18. A. Papoulis, "Probability, Random Variables, and Stochastic Processes," MacGraw-Hill, New York, 1984.
19. H. U. Simon, General bounds on the number of examples needed for learning probabilistic concepts, J. Comput. System Sci. 52, No. 2 (1996), 239-254.
20. V. N. Vapnik and A. Y. Chervonenkis, On the uniform convergence of relative frequencies of events to their probabilities, Theory Probab. and Its Appl. 16, No. 2 (1971), 264-280.