MetaCart Sign in to MyCiteSeerX

Include Citations | Advanced Search | Help

Disambiguated Search | Include Citations | Advanced Search | Help

Learning to Classify Incomplete Examples (1993) [10 citations — 2 self]

by Dale Schuurmans ,  Russell Greiner
In Computational Learning Theory and Natural Learning Systems: Addressing Real World Tasks
Add To MetaCart

Abstract:

Most research on supervised learning assumes the attributes of training and test examples are completely specified. Real-world data, however, is often incomplete. This paper studies the task of learning to classify incomplete test examples, given incomplete (resp., complete) training data. We first show that the performance task of classifying incomplete examples requires the use of default classification functions which demonstrate nonmonotonic classification behavior. We then extend the standard pac-learning model to allow attribute values to be hidden from the classifier, investigate the robustness of various learning strategies, and study the sample complexity of learning classes of default classification functions from examples. 1 Introduction The central task of most expert systems is classifying objects from some domain of application; i.e., determining whether a particular object belongs to a specified class, given a description of that object (Clancey, 1985). For example, a ...

Citations

4701 Probabilistic Reasoning in Intelligent Systems – Pearl - 1988
2573 Classification and Regression Trees – Breiman, Friedman, et al. - 1984
1328 A theory of the learnable – Valiant - 1984
525 Learnability and the Vapnik-Chervonenkis dimension – Blumer, Ehrenfeucht, et al. - 1989
507 Statistical Analysis with Missing Data – Little, Rubin - 2002
302 Decision theoretic generalizations of the PAC model for neural net and other learning applications – Haussler - 1992
247 Heuristic classification – Clancey - 1985
179 Learning from noisy examples – Angluin, Laird - 1988
172 A general lower bound on the number of examples needed for learning – Ehrenfeucht, Haussler, et al. - 1988
168 Efficient distribution-free learning of probabilistic concepts – Kearns, Schapire - 1990
154 The Need for Biases in Learning Generalizations – Mitchell - 1980
141 Connectionist learning of belief networks – Neal - 1992
135 On the hardness of approximate reasoning – Roth - 1996
123 Learning in the presence of malicious errors – Kearns, Li - 1988
99 Concept learning and heuristic classification in weak theory domains – Porter, Bareiss, et al. - 1990
95 Unknown attribute values in induction – Quinlan - 1989
68 Nonmonotonic reasoning – Reiter - 1987
31 Learning k-DNF with noise in the attributes – Shackelford, Volper - 1988
29 Learning complicated concepts reliably and usefully – Rivest, Sloan - 1988
19 Learning default concepts – Schuurmans, Greiner - 1994
16 Evidential probability – Kyburg - 1991
4 Exploiting the absence of irrelevant information – Hancock, Greiner, et al. - 1994
1 Supervised learning from real and discrete incomplete data – Ghahramani, Jordan - 1994
View or Download | Add to My Collection | Correct Errors