Learning from a consistently ignorant teacher

Journal of Computer and System Sciences

Volumn 52, Issue 3, 1996, Pages 471-492

  Frazier, Michael ^a   Goldman, Sally ^b   Mishra, Nina ^c   Pitt, Leonard ^c  

^a ABILENE CHRISTIAN UNIVERSITY   (United States)

^b WASHINGTON UNIVERSITY IN ST LOUIS   (United States)

^c University of Illinois at Urbana Champaign   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION THEORY; BOOLEAN FUNCTIONS; COMPUTATION THEORY; LEARNING ALGORITHMS; MATHEMATICAL MODELS; RANDOM PROCESSES; SET THEORY;

COMPUTATIONAL LEARNING THEORY; LEARNABILITY; TERNARY LABELLING;

LEARNING SYSTEMS;

EID: 0030164934     PISSN: 00220000     EISSN: None     Source Type: Journal    
DOI: 10.1006/jcss.1996.0035     Document Type: Article

References (64)

1. D. Angluin, M. Frazier, and L. Pitt, Learning conjunctions of Horn clauses, Mach. Learning 9 (1992), 147-164.
2. D. Angluin, L. Hellerstein, and M. Karpinski, Learning read-once formulas with queries, J. Assoc. Comput. Mach. 40 (1993), 185-210.
3. H. Aizenstein, L. Hellerstein, and L. Pitt, Read-thrice DNF is hard to learn with membership and equivalence queries, in "Proc. of the 33rd Symposium on the Foundations of Comp. Sci.," pp. 523-532, IEEE Computer Society Press, Los Alamitos, CA, 1992. (A revised manuscript, with additional results, is Aizenstein, Hegedus, Hellerstein, and Pitt, Complexity theoretic hardness results for query learning, Comput. Complexity, to appear).
4. D. Angluin and M. Kriķis, Learning with malicious membership queries and exceptions, in "Proc. 7th Annual ACM Conference on Computational Learning Theory," pp. 57-66, ACM Press, New York, NY, 1994.
5. D. Angluin and M. Kharitonov, J. Comput. System Sc. 50 (1995), 336-355.
6. P. Auer, S. Kwek, W. Maass, and M. Warmuth, On-line prediction of depth two linear threshold circuits, manuscript in preparation.
7. D. Angluin and P. Laird, Learning from noisy examples, Machine Learning 2, No. 4 (1988), 343-370.
8. D. Angluin, "Learning k-Term DNF Formulas Using Queries and Counterexamples," Technical Report YALEU/DCS/RR-559, Department of Computer Science, Yale University, August 1987.
9. D. Angluin, Learning regular sets from queries and counterexamples, Inform. and Comput. 75, No. 2 (1987), 87-106.
10. D. Angluin, Queries and concept learning, Machine Learning 2, No. 4(1988), 319-342.
11. D. Angluin, Negative results for equivalence queries, Machine Learning 5 (1990), 121-150.
12. D. Angluin, "Exact Learning of μ-DNF Formulas with Malicious Membership Queries," Technical Report YALEU/DCS/TR-1020, Yale University, 1994.
13. H. Aizenstein and L. Pitt, Exact learning of read-twice DNF formulas, in "Proc. 32th Annual IEEE Symposium on Foundations of Computer Science," pp. 170-179, IEEE Computer Society Press, New York, 1991.
14. D. Angluin and D. Slonim, Randomly fallible teachers: Learning monotone DNF with an incomplete membership oracle, Machine Learning 14, No. 7 (1994), 7-26.
15. D. Angluin and L. G. Valiant, Fast probabilistic algorithms for hamiltonian circuits and matchings, J. Comput. System Sc. 18, No. 2(1979), 155-193.
16. N. Bshouty, Z. Chen, and S. Homer, On learning discretized geometric concepts, in "Proc. of the 35th Symposium on the Foundations of Computer Science," pp. 54-63, IEEE Computer Society Press, Los Alamitos, CA, 1994.
17. A. Blumer, A. Ethrenfeucht, D. Haussler, and M. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, J. Assoc. Comput. Mach. 36, No. 4 (1989), 929-965.
18. N. Bshouty, P. Goldberg, S. Goldman, and D. Mathias, "Exact Learning of Discretized Geometric Concepts," Tech. Rep. WUCS-94-19, Washington University, July 1994.
19. N. Bshouty, S. Goldman, and D. Mathias, Noise-tolerant parallel learning of geometric concepts, in "Proc. 8th Annual ACM Conference on Computational Learning Theory," pp. 345-352, ACM Press, New ACM Press, New York, 1995.
20. N. Bshouty, S. Goldman, D. Mathias, S. Suri, and H. Tamaki, Noise-tolerant distribution-free learning of general geometric concepts, manuscript in preparation.
21. N. Bshouty, T. Hancock, and L. Hellerstein, Learning Boolean read-once formulas with arbitrary symmetric and constant fan-in gates, in "Proc. 5th Annual Conference on Computational Learning Theory," pp. 1-15, ACM Press, New York, 1992.
22. N. Bshouty, T. Hancock, and L. Hellerstein, Learning arithmetic read-once formulas, SIAM J. Comput. 24, No. 4 (1995), 706-735.
23. A. Blum, Separating distribution-free and mistake-bound learning models over the Boolean domain, SIAM J. Comput. 23, No. 5 (1994), 990-1000.
24. A. Blum and S. Rudich, Fast learning of k-term DNF formulas with queries, in "Proc. of the 24th Symposium on Theory of Computing," pp. 382-389, ACM Press, New York, 1992.
25. N. Bshouty, Exact learning Boolean functions via the monotone theory, Inform. Comput. 123, No. 1 (1995), 146-153.
26. Z. Chen and S. Homer, The bounded injury priority method and the learnability of unions of rectangles, unpublished manuscript, 1994.
27. W. Cohen and H. Hirsh, Learning the CLASSIC description logic: Theoretical and experimental results, in "Principles of Knowledge Representation and Reasoning: Proceedings of the Fourth International Conference (KR94)," Morgan Kaufmann, San Mateo, CA, 1994.
28. W. Cohen and H. Hirsh, Learnability of description logics with equality constraints, Machine Learning 17, No. 2-3 (1994), 169-199.
29. Z. Chen, Learning unions of two rectangles in the plane with equivalence queries, in "Proc. 6th Annual Conference on Computational Learning Theory," pp. 243-252, ACM Press, New York, 1993.
30. Z. Chen and W. Maass, On-line learning of rectangles, in "Proc. 5th Annual Workshop on Computational Learning Theory," pp. 16-28, ACM Press, New York, 1992.
31. M. Frazier and L. Pitt, CLASSIC learning, in "Proc. 7th Annual ACM Conference on Computational Learning Theory," pp. 23-24, ACM Press, New York, 1994; also Machine Learning, to appear.
32. M. Frazier and L. Pitt, CLASSIC learning, in "Proc. 7th Annual ACM Conference on Computational Learning Theory," pp. 23-24, ACM Press, New York, 1994; also Machine Learning, to appear.
33. P. Goldberg, S. Goldman, and D. Mathais, Learning unions of boxes with membership and equivalence queries, in "Proc. 7th Annual ACM Conference on Computational Learning Theory," pp. 198-207, ACM Press, New York, 1994.
34. S. Goldman, M. Kearns, and R. Schapire, Exact identification of circuits using fixed points of amplification functions, SIAM J. Comput. 22, No. 4 (1993), 705-726.
35. C. Gunter, T. Ngair, P. Panangaden, and D. Subramanian, The common order-theoretic structure of version spaces and atms's, in "Proceedings of the National Conference on Artificial Intelligence," pp.500-505, AAAI Press/MIT Press, Anaheim, CA, 1991.
36. S. Goldman and R. Sloan, Can PAC learning algorithms tolerate random noise, Algorithmica 14, No. 1 (1995).
37. T. Hancock, Learning 2μ-DNF formulas and kμ decision trees, in "Proc. 4th Annual Workshop on Computational Learning Theory," pp. 199-209, Morgan Kaufmann, San Mateo, CA, 1991.
38. D. Haussler, "Generalizing the PAC Model for Neural Net and Other Learning Applications," Tech. Rep. UCSC-CRL-89-3U, University of California Santa Cruz, Sep. 1989.
39. H. Hirsh, Theoretical underpinnings of version spaces, in "Proceedings of the Twelfth Joint International Conference on Artificial Intelligence," pp. 665-670, Sydney, Australia, 1991.
40. D. Haussler, M. Kearns, N. Littlestone, and M. Warmuth, Equivalence of models for polynomial learnability, Inform. and Comput. 95, No. 2 (1991), 129-161.
41. D. Haussler, N. Littlestone, and M. Warmuth, Predicting {0, 1} functions on randomly drawn points, Inform. Comput. 115, No. 2 (1994), 284-293.
42. J. Hopcroft and J. Ullman, "Introduction to Automata Theory, Languages, and Computation," Addison-Wesley, Reading, MA, 1979.
43. J. Jackson, Learning DNF under the uniform distribution, in "Proc. of the 35th Symposium on the Foundations of Computer Science," pp. 42-53, IEEE Computer Society Press, Los Alamitos, CA, 1994.
44. M. Kearns, Efficient noise-tolerant learning from statistical queries, in "Proc. 25th Annual ACM Symposium on Theory of Computing," pp. 392-401, ACM Press, New York, 1993.
45. M. Kearns and M. Li, Learning in the presence of malicious errors, SIAM J. Comput. 22 (1993), 807-837.
46. S. Kwek and L. Pitt, Polynomial-time learning of intersections of halfspaces, Manuscript in preparation, 1995.
47. M. Kearns and R. Schapire, Efficient distribution-free learning of probabilistic concepts, J. Comput. System Sci. 48, No. 3(1994), 464-497.
48. M. Kearns and L. Valiant, Cryptographic limitations on learning Boolean formulae and finite automata, J. Assoc. Comput. Mach. 41, No. 1 (1994), 67-95.
49. P. Laird, "Learning from Good and Bad Data," Kluwer International Series in Engineering and Computer Science, Kluwer Academic, Boston, 1988.
50. P. Long and M. Warmuth, Composite geometric concepts and polynomial predictability, Inform. and Comput. 113, No. 2 (1994), 230-252.
51. T. Mitchell, "Version Spaces: An Approach to Concept Learning," Ph. D. thesis, Stanford University, Dec. 1978.
52. T. Mitchell, Generalization as search, Artif. Intell. 18 (1982), 203-226.
53. W. Maass and M. Warmuth, Efficient learning with virtual threshold gates, in "Proc. XII International Conference on Machine Learning," pp. 378-386, Morgan Kaufmann, San Francisco, CA, 1995.
54. K. Pillaipakkamnatt and V. Raghavan, On the limits of proper learnability of subclasses of DNF formulas, "Proc. 7th Annual ACM Conference on Computational Learning Theory," pp. 118-129, ACM Press, New York, 1994; also Machine Learning, to appear.
55. K. Pillaipakkamnatt and V. Raghavan, On the limits of proper learnability of subclasses of DNF formulas, "Proc. 7th Annual ACM Conference on Computational Learning Theory," pp. 118-129, ACM Press, New York, 1994; also Machine Learning, to appear.
56. K. Pillaipakkamnatt and V. Raghavan, Read-twice DNF formulas are properly learnable, Inform. Comput. 122, No. 2 (1995), 236-267.
57. L. Pitt and M. Warmuth, Prediction preserving reducibility, J. Comput. System Sci. 41, No. 3 (1990), 430-167.
58. D. Ron and R. Rubinfeld, Learning fallible deterministic finite automata, Machine Learning 18, Nos. 2/3 (1995), 149-186.
59. Y. Sakakibara, On learning from queries and counterexamples in the presence of noise, Inform. Process. Lett. 37, No. 5 (1991), 279-284.
60. Y. Sakakipara and R. Siromoney, A noise model on learning sets of strings, in "Proc. 5th Annual Workshop on Computational Learning Theory," pp. 295-302, ACM Press, New York, 1992.
61. R. Sloan, Types of noise in data for concept learning, in "Proc. 1st Annual Workshop on Computational Learning Theory," pp. 91-96, Morgan Kaufmann, San Mateo, CA, 1988.
62. R. H. Sloan and G. Turán, Learning with queries but incomplete information, in "Proc. 7th Annual ACM Conference on Computational Learning Theory," pp. 237-245, ACM Press, New York, 1994.
63. G. Shackelford and D. Volper, Learning k-DNF with Noise in the Attributes, in "Proc. 1st Annual Workshop on Computational Learning Theory," pp. 97-103, Morgan Kaufmann, San Mateo, CA, 1988.
64. L. Valiant, A theory of the learnable, Comm. ACM 27, No. 11 (1984), 1134-1142.