Learning From Examples With Unspecified Attribute Values

Learning From Examples With Unspecified Attribute Values (1998)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Sally A. Goldman , Stephen S. Kwek , Stephen D. Scott

Venue:	In Proc. 10th Annu. Conf. on Comput. Learning Theory
Citations:	19 - 1 self

BibTeX

@INPROCEEDINGS{Goldman98learningfrom,
    author = {Sally A. Goldman and Stephen S. Kwek and Stephen D. Scott},
    title = {Learning From Examples With Unspecified Attribute Values},
    booktitle = {In Proc. 10th Annu. Conf. on Comput. Learning Theory},
    year = {1998},
    pages = {231--242},
    publisher = {ACM Press}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

We introduce the UAV learning model in which some of the attributes in the examples are unspecified. In our model, an example x is classified positive (resp., negative) if all possible assignments for the unspecified attributes result in a positive (resp., negative) classification. Otherwise the classification given to x is "?" (for unknown). Given an example x in which some attributes are unspecified, the oracle UAV-MQ responds with the classification of x. Given a hypothesis h, the oracle UAV-EQ returns An earlier version appears in the Tenth Annual ACM Conferenceon ComputationalLearning Theory, 1997 y Supported in part by NSF NYI Grant CCR-9357707 with matching funds provided by Xerox PARC and WUTA. an example x (that could have unspecified attributes) for which h(x) is incorrect. We show that any class learnable in the exact model using the MQ and EQ oracles is also learnable in the UAV model using the MQ and UAV-EQ oracles as long as the counterexamples provided by the UAV-...

Citations

3144	Classification and Regression Trees - Breiman, Friedman, et al. - 1984
1515	A theory of the learnable - Valiant - 1984
583	Queries and concept learning - Angluin - 1988
440	Learning regular sets from queries and counterexamples - Angluin - 1987
182	Efficient distributionfree learning of probabilistic concepts - Kearns, Schapire - 1994
158	Learning in the presence of malicious errors - Kearns, Li - 1993
101	Learning conjunctions of Horn Clauses - Angluin, Frazier, et al. - 1992
101	Concept learning and heuristic classification in weak-theory domains - Porter, Bareiss, et al. - 1990
98	Learning read-once formulas with queries - Angluin, Hellerstein, et al. - 1993
95	Redundant noisy attributes, attribute errors, and linear-threshold learning using Winnow - Littlestone - 1991
95	Unknown attribute values in induction - Quinlan - 1989
82	Exact Learning via the Monotone Theory - Bshouty - 1993
72	Oracles and queries that are sufficient for exact learning - Bshouty, Cleve, et al. - 1996
48	Types of noise in data for concept learning - Sloan - 1988
47	Fast Learning of k-term DNF formulas with Queries - Blum, Rudich - 1992
34	Exact Learning of Read-Twice DNF formulas - Aizenstein, Pitt - 1991
33	Can PAC learning algorithms tolerate random attribute noise - Goldman, Sloan - 1995
33	Learning k-DNF with noise in the attributes - Shackelford, Volper - 1988
29	Learning with restricted focus of attention - Ben-David, Dichterman - 1998
27	Learning with unreliable boundary queries - Blum, Chalasani, et al. - 1998
27	Learning arithmetic read-once formulas - Bshouty, Hancock, et al. - 1992
24	Simple learning algorithms using divide and conquer - BSHOUTY - 1995
23	Randomly fallible teachers: Learning monotone DNF with an incomplete membership oracle - Angluin, Slonim - 1994
22	Learning from a Consistently Ignorant Teacher - Frazier, Goldman, et al. - 1994
20	Learning from Good and Bad Data. Kluwer international series in engineering and computer science - Laird - 1988
20	Learning default concepts - Schuurmans, Greiner - 1994
17	Learning active classifiers - GREINER, GROVE, et al. - 1996
17	On learning from queries and counterexamples in the presence of noise - Sakakibara - 1991
14	Learning with Malicious Membership Queries and Exceptions - Angluin, Krikis - 1994
14	On restricted-focus-ofattention learnability of Boolean functions - Birkendorf, Dichterman, et al. - 1998
11	Learning read-once formulas using membership queries - Hellerstein, Karpinski - 1989
10	Learning with queries but incomplete information - Sloan, Turan - 1994
8	An algorithm to learn read-once threshold formulas, and transformations between learning models - Bshouty, Hancock, et al. - 1994
3	Identifying -decision trees and -formulas with constrained instance queries - Hancock - 1989
2	Learning to Classify Incomplete Examples, chapter 6 - Schuurmans, Greiner - 1997