Classification accuracy based on observed margin

Algorithmica (New York)

Volumn 22, Issue 1-2, 1998, Pages 157-172

  Shawe Taylor, J ^a  

^a UNIVERSITY OF LONDON   (United Kingdom)

Author keywords

Agnostic learning; Computational learning theory; Fat shattering; Generalization; Large margin; Pac estimates

Indexed keywords

EID: 0004154449     PISSN: 01784617     EISSN: None     Source Type: Journal    
DOI: 10.1007/PL00013827     Document Type: Article

References (14)

1. N. Alon, S. Ben-David, N. Cesa-Bianchi, and D. Haussler, Scale-Sensitive Dimensions, Uniform Convergence, and Learnability, Journal of the ACM, 44 (1997), 615-631.
2. M. Anthony and J. Shawe-Taylor, A Result of Vapnik with Applications, Discrete Applied Mathematics, 47(1993), 207-217.
3. P. Bartlett, The Sample Complexity of Pattern Classification with Neural Networks: the Size of the Weights Is More Important than the Size of the Network, Technical Report, Department of Systems Engineering, Australian National University, May 1996.
4. A. Blumer, A. Ehrenfeucht, D. Haussler, and M. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, Journal of the ACM, 36 (1989), 929-965.
5. B. E. Boser, I. M. Guyon, and V. N. Vapnik, A Training Algorithm for Optimal Margin Classifiers, pages 144-152 in Proceedings of the Fifth Annual Workshop on Computational Learning Theory, Pittsburgh, ACM, New York, 1992.
6. M. J. Kearns and R. E. Schapire, Efficient Distribution-Free Learning of Probabilistic Concepts, pages 382-391 in Proceedings of the 31st Symposium on the Foundations of Computer Science, IEEE Computer Society Press, Los Alamitos, CA, 1990.
7. D. J. C. MacKay, Bayesian Methods for Adaptive Models, Ph.D. Thesis, Caltech, 1991.
8. D. Pollard, Convergence of Stochastic Processes, Springer-Verlag, New York, 1984.
9. J. Shawe-Taylor, Confidence Estimates of Classification Accuracy on New Examples, pages 260-271 in Proceedings of the EuroCOLT'91 Conference on Computational Learning Theory, Lecture Notes in Artificial Intelligence, 1208, Springer-Verlag, New York, 1997.
10. J. Shawe-Taylor, P. Bartlett, R. Williamson, and M. Anthony, Structural Risk Minimization over Data-Dependent Hierarchies, NeuroCOLT Technical Report NC-TR-96-51, ftp://ftp.dcs.rhbnc.ac.uk/pub/ neurocolt/tech_reports.
11. Also to appear in IEEE Transactions on Information Theory, 1998.
12. V. N. Vapnik, Estimation of Dependences Based on Empirical Data, Springer-Verlag, New York, 1982.
13. V. N. Vapnik, The Nature of Statistical Learning Theory, Springer-Verlag, New York, 1995.
14. V. N. Vapnik and A. Ja. Chervonenkis, On the Uniform Convergence of Relative Frequencies of Events to their Probabilities, Theory of Probability and Applications, 16 (1971), 264-280.