Complexity in the case against accuracy estimation

Theoretical Computer Science

Volumn 301, Issue 1-3, 2003, Pages 143-165

  Nock, Richard ^a  

^a GRIMAAG   (France)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTATIONAL COMPLEXITY; DATA MINING; DECISION THEORY; LOGIC PROGRAMMING;

RECEIVER OPERATING CHARACTERISTIC ANALYSIS;

COMPUTER SCIENCE;

EID: 0038371419     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0304-3975(02)00573-X     Document Type: Article

References (29)

1. S. Boucheron, Théorie de l'apprentissage, de l'approche formelle aux enjeux cognitifs. Hermes, 1992.
2. W.W. Cohen, Text categorization and relational learning, in: Proc. 12th Internat. Conf. on Machine Learning, 1995, pp. 124-132.
3. P. Domingos, MetaCost: a general method for making classifiers cost-sensitive, in: Proc. 5th Internat. Conf. on Knowledge Discovery in Databases, 1999, pp. 155-164.
4. S. Dzeroski, S. Muggleton, S. Russel, Pac-learning of determinate logic programs, in: Proc. 5th Internat. Conf. on Computational Learning Theory, 1992, pp. 128-137.
5. Egan J.P. Signal detection theory and ROC analyses. 1975;Academic Press, New York.
6. Friedman J., Hastie T., Tibshirani R. Additive logistic regression. a statistical view of boosting Ann. Statist. 28:2000;337-374.
7. M. Garey, D. Johnson, Computers and Intractability, a guide to the theory of NP-Completeness, Bell Telephone Laboratories, 1979.
8. 1-ε, in: Proc. 37th IEEE Symp. on the Foundations of Computer Science, 1996, pp. 627-636.
9. K.-U. Höffgen, H. Simon, Robust trainability of single neurons, in: Proc. 5th Internat. Conf. on Computational Learning Theory, 1992.
10. Holte R. Very simple classification rules perform well on most commonly used datasets. Mach. Learning. 11:1993;63-91.
11. P. Jappy, R. Nock, O. Gascuel, Negative robust learning results for horn clause programs, in: Proc. 13th Internat. Conf. on Machine Learning, Morgan Kauffman, Los Altos, CA, 1996, pp. 258-265.
12. M. Kearns, M. Li, L. Pitt, L. Valiant, On the learnability of boolean formulae, in: Proc. 19th ACM Symp. on the Theory of Computing, 1987, pp. 285-295.
13. J.-U. Kietz, Some lower bounds for the computational complexity of inductive logic programming, in: Proc. 8th European Conf. on Machine Learning, 1993, pp. 115-123.
14. Kietz J., Dzeroski S. Inductive logic programming and learnability. Sigart Bull. 5:1994;22-32.
15. õ(n1/3), in: Proc. 33th ACM Symp. on the Theory of Computing, 2001, pp. 258-265.
16. Kukar M., Besic N., Kononenko I., Auersperg M., Robnik-Sikonja M. Prognosing the survival time of the patients with anaplastic thyroid carcinoma using machine learning. Lavrac N., Karavnou E., Zupan B. Intelligent data analysis in medicine and pharmacology. 1997;116-129 Kluwer Academic Publishers, Dordrecht.
17. Kubat M., Holte R.C., Matwin S. Machine Learning for the detection of oil spills in satellite radar images. Mach. Learning. 30:1998;195-215.
18. Nock R., Gascuel O. On learning decision committees. Proc. 12th Internat. Conf. on Machine Learning. 1995;413-420 Morgan Kaufmann, Los Altos, CA.
19. Nock R., Jappy P. On the power of decision lists. Proc. 15th Internat. Conf. on Machine Learning. 1998;413-420 Morgan Kaufmann, Los Altos CA.
20. F. Provost, T. Fawcett, Analysis and visualization of classifier performance: comparison under imprecise class and cost distributions, in: Proc. 3rd Internat. Conf. on Knowledge Discovery in Databases, 1997, pp. 43-48.
21. F. Provost, T. Fawcett, Robust classification systems for imprecise environments, in: Proc. 15th National Conf. on Artificial Intelligence, 1998, pp. 706-713.
22. F. Provost, T. Fawcett, R. Kohavi, The case against accuracy estimation for comparing induction algorithms, in: Proc. 15th Internat. Conf. on Machine Learning, 1998, pp. 445-453.
23. R.E. Schapire, Y. Singer, Improved boosting algorithms using confidence-rated predictions, in: Proc. 11th Internat. Conf. on Computational Learning Theory, 1998, pp. 80-91.
24. Sebban M., Nock R. A hybrid filter/wrapper approach of feature selection using information theory. Pattern Recognition. 35:2002;835-846.
25. S. Slattery, M. Craven, Combining statistical and relational methods for learning in hypertext domains, in: Proc. 8th Internat. Conf. on Inductive Logic Programming, 1998, pp. 38-52.
26. A. Srinivasan, Applications of ILP to problems in chemistry and biology, in: Invited talk at the 8th Internat. Conf. on Inductive Logic Programming, 1998.
27. Valiant L.G. A theory of the learnable. Commun. ACM. 27:1984;1134-1142.
28. L.G. Valiant, Learning disjunctions of conjunctions, in: Proc. 9th Internat. Joint Conf. on Artificial Intelligence, 1985, pp. 560-566.
29. Vapnik V. Statistical learning theory. 1998;John Wiley, New York.