Knowing what doesn't matter: Exploiting the omission of irrelevant data

Artificial Intelligence

Volumn 97, Issue 1-2, 1997, Pages 345-380

  Greiner, Russell ^a,e   Grove, Adam J ^b   Kogan, Alexander ^c,d  

^a SIEMENS CORPORATE RESEARCH   (United States)

^b NEC LABORATORIES AMERICA   (United States)

^c RUTGERS UNIVERSITY   (United States)

^d the State University of New Jersey   (United States)

^e UNIVERSITY OF ALBERTA   (Canada)

Author keywords

Adversarial noise; Blocked attributes; Decision trees; Diagnosis; DNF; Irrelevant values; Learnability; Theory revision

Indexed keywords

DECISION THEORY; LEARNING ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; TREES (MATHEMATICS);

SUPERFLUOUS VALUE BLOCKING;

NEURAL NETWORKS;

EID: 0031380978     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/s0004-3702(97)00048-9     Document Type: Article

References (38)

1. D. Angluin, Computational learning theory: survey and selected bibliography, in: Proceedings 24th Annual ACM Symposium on Theory of Computing (ACM Press, New York, 1992) 351-369.
2. A. Blum, Learning boolean functions in an infinite attribute space, Machine Learning 9 (4) (1992) 373-386.
3. A. Blum, L. Hellerstein and N. Littlestone, Learning in the presence of finitely or infinitely many irrelevant attributes, J. Comput. System Sci. 50 (1) (1995) 32-40.
4. L. Breiman, J. Friedman, J. Olshen and C. Stone, Classification and Regression Trees (Wadsworth and Brooks, Monterey, CA, 1984).
5. H. Chernoff, A measure of asymptotic efficiency for tests of a hypothesis based on the sums of observations, Ann. Math. Statist. 23 (1952) 493-507.
6. A. Ehrenfeucht and D. Haussler, Learning decision trees from random examples, Inform. and Comput. 82 (1989) 231-246.
7. S.A. Goldman and H.D. Mathias, Teaching a smarter learner, J. Comput. System Sci. 52 (2) (1996) 255-267.
8. S.A. Goldman and R.A. Sloan, Can PAC learning algorithms tolerate random attribute noise?, Algorithmica 14 (1) (1995).
9. R. Greiner, The complexity of theory revision, in: Proceedings IJCAI-95, Montreal, Que. (1995).
10. R. Greiner, A. Grove and A. Kogan, Exploiting the omission of irrelevant data, in: Proceedings 13th International Machine Learning Conference, Bari, Italy (Morgan Kaufmann, Los Altos, CA, 1996).
11. D. Haussler, M. Kearns, N. Littlestone and M.K. Warmuth, Equivalence of models for polynomial learnability, Inform. and Comput. 95 (2) (1991) 129-161.
12. G.H. John, R. Kohavi and K. Pfleger, Irrelevant features and the subset selection problem, in: Proceedings 11th International Machine Learning Conference, New Brunswick, NJ (Morgan Kaufmann, Los Altos, CA, 1994) 121-129.
13. M. Kearns and M. Li, Learning in the presence of malicious errors, SIAM J. Comput. 22 (1993) 807-837.
14. M. Kearns, M. Li, L. Pitt and L. Valiant, On the learnability of boolean formulae, in: Proceedings 19th Symposium on the Theory of Computing, New York (1987) 285-295.
15. M. Kearns, Y. Mansour, D. Ron, R. Rubinfeld, R. Schapire and L. Sellie, On the learnabilty of discrete distributions, in: Proceedings 26th ACM Symposium on Theory of Computing, Montreal, Que. (1994) 273-282.
16. M.J. Kearns, R.E. Schapire and L.M. Sellie, Toward efficient agnostic leaning, in: Proceedings 5th Annual Workshop on Computational Learning Theory (ACM Press, New York, 1992) 341-352.
17. E. Kushilevitz and D. Roth, On learning visual concepts and DNF formulae, in: Proceedings 6th Annual Workshop on Computational Learning Theory, Santa Cruz, CA (ACM Press, New York, 1993) 317-326.
18. P. Langley, G. Drastal, R. Bharat Rao and R. Greiner, Theory revision in fault hierarchies, in: Proceedings 5th International Workshop on Principles of Diagnosis (DX-94), New Paltz, NY (1994).
19. J.A. Little and D.B. Rubin, Statistical Analysis with Missing Data (Wiley, New York, 1987).
20. N. Littlestone, Learning quickly when irrelevant attributes abound: a new linear-threshold algorithm, Machine Learning J. 2 (1988) 285-318.
21. N. Littlestone, Redundant noisy attributes, attribute errors and linear threshold learning using Winnow, in: Proceedings 4th Annual Workshop on Computational Learning Theory (Morgan Kaufmann, San Mateo, CA, 1991) 147-156.
22. S. Mahadevan and P. Tadepalli, Quantifying prior determination knowledge using the PAC learning model, Machine Learning 17 (1994) 69-105.
23. R. Mooney, A preliminary PAC analysis of theory revision, in: T. Petsche and S. Hanson, eds., Proceedings 3rd Annual Workshop on Computational Learning Theory and Natural Learning Systems (CLNL-92) (MIT Press, Cambridge, MA, 1994).
24. S. Muggleton and W. Buntine, Machine invention of first order predicates by inverting resolution, in: Proceedings 5th International Conference on Machine Learning, Ann Arbor, MI (Morgan Kaufmann, Los Altos, CA, 1988) 339-351.
25. D. Ourston and R.J. Mooney, Changing the rules: a comprehensive approach to theory refinement, in: Proceedings AAAI-90, Boston, MA (1990) 815-820.
26. B.W. Porter, R. Bareiss and R.C. Holte, Concept learning and heuristic classification in weak-theory domains, Artificial Intelligence 45 (1-2) (1990) 229-263.
27. J.R. Quinlan, C4.5: Programs for Machine Learning (Morgan Kaufmann, San Mateo, CA, 1992).
28. R.L. Rivest, Learning decision lists, Machine Learning 2 (3) (1987) 229-246.
29. K. Ruberg, S.M. Cornick and K.A. James, House calls: building and maintaining a diagnostic rule-base, in: Proceedings 3rd Knowledge Acquisition for Knowledge-Based Systems Workshop (1988).
30. S. Russell, The Use of Knowledge in Analogy and Induction (Morgan Kaufmann, Los Altos, CA, 1989).
31. D. Schuurmans and R. Greiner, Learning to Classify Incomplete Examples (MIT Press, Cambridge, MA, 1997) Chapter 6.
32. D. Schuurmans and R. Greiner, Learning default concepts, in: Proceedings 10th Canadian Conference on Artificial Intelligence, Banff, Alberta (1994) 519-523.
33. G. Shackelford and D. Volper, Learning k-DNF with noise in the attributes, in: Proceedings 2nd Annual Workshop on Computational Learning Theory (Morgan Kaufmann, Los Altos, CA, 1988) 97-103.
34. J.W. Shavlik and T.G. Dietterich, Readings in Machine Learning (Morgan Kaufmann, Los Altos, CA, 1990).
35. G. Towell, Symbolic knowledge and neural networks: Insertion, refinement and extraction, Ph.D. Thesis, University of Wisconsin, Madison, WI (1991).
36. P.D. Turney, Cost-sensitive classification: empirical evaluation of a hybrid genetic decision tree induction algorithm, J. Artif. Intell. Research 2 (1995) 369-409.
37. L.G. Valiant, A theory of the learnable, Comm. ACM 27 (11) (1984) 1134-1142.
38. J. Wogulis and M.J. Pazzani, A methodology for evaluating theory revision systems: results with Audrey II, in: Proceedings IJCAI-93, Chambery, France (1993) 1128-1134.