Generalization error of combined classifiers

Journal of Computer and System Sciences

Volumn 65, Issue 2, 2002, Pages 415-438

  Mason, Llew ^a   Bartlett, Peter L ^a   Golea, Mostefa ^a  

^a AUSTRALIAN NATIONAL UNIVERSITY   (Australia)

Author keywords

Boosting; Decision trees; Margins analysis; Neural networks; Voting methods

Indexed keywords

ASYNCHRONOUS MACHINERY; COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; EMBEDDED SYSTEMS; FORMAL LANGUAGES; GRAPHIC METHODS; MATHEMATICAL MODELS; PROBLEM SOLVING;

DECISION TREES; EQUIVALENCE PROBLEMS; MONOID THEORY; THRESHOLD LAYERS;

FUNCTIONS;

EID: 23844481466     PISSN: 00220000     EISSN: 10902724     Source Type: Journal    
DOI: 10.1006/jcss.2002.1854     Document Type: Article

References (17)

1. M. Anthony and J. Shawe-Taylor, A result of Vapnik with applications, Discrete Appt. Math. 47 (1993), 207-217.
2. P. L. Bartlett, The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network, IEEE Trans. Inform. Theory 44(2) (1998), 525-536.
3. E. B. Baum and D. Haussler, What size net gives valid generalization? Neural Comput. 1 (1989), 150-160.
4. L. Breiman, Bagging predictors, Mach. Learning 24(2) (1996), 123-140.
5. L. Breiman, Arcing classifiers, Ann. Statist. 26(3) (1998), 801-849.
6. L. Breiman, "Prediction games and arcing Algorithms," Technical Report 504, Department of Statistics, University of California, Berkeley, 1998.
7. L. Devroye, L. Györfi, and G. Lugosi, "A Probabilistic Theory of Pattern Recognition," Applications of Mathematics: Stochastic Modelling and Applied Probability, Vol. 31, Springer, New York, 1996.
8. Y. Freund and R. E. Schapire, Experiments with a new boosting algorithm, in "Machine Learning: Proceedings of the 13th International Conference," pp. 148-156, 1996.
9. Y. Freund and R. E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting, J. Comput. System Sci. 55(1) (1997), 119-139.
10. M. Golca, P. L. Bartlett, W. S. Lee, and L. Mason, Generalization in decision trees and DNF: Does size matter? in "Advances in Neural Information Processing Systems," Vol. 10, pp. 259-265. MIT Press, New York, 1998.
11. A. Grove and D. Schuurmans, Boosting in the limit: Maximizing the margin of learned ensembles, in "Proceedings of the 15th National Conference on Artificial Intelligence," pp. 692-699, 1998.
12. W. Hoeffding, Probability inequalities for sums of bounded random variables, J. Amer. Statist. Assoc. 58(1963), 13-30.
13. A. Kowalczyk and H. Ferra, Developing higher order networks with empirically selected units, IEEE Trans. Neural Networks 5(5) (1993), 698-711.
14. L. Mason, P. L. Bartlett, and M. Golea, Generalization in threshold networks, combined decision trees and combined mask perceptrons, in "Proceedings of the Ninth Australian Conference on Neural Networks," pp. 84-88, 1998.
15. N. Sauer, On the density of families of sets, J. Combin. Theory Ser. A 13 (1972), 145-147.
16. R. E. Schapire, Y. Freund, P. Bartlett, and W. S. Lee, Boosting the margin: A new explanation for the effectiveness of voting methods, Ann. Statist. 26(5) (1998), 1651-1686.
17. V. N. Vapnik and A. Y. Chervonenkis, On the uniform convergence of relative frequencies of events to their probabilities, Theory Probab. Appl. 16(2) (1971), 264-280.