Analyses of instance-based learning algorithms

Authors:
Marc K. Albert;David W. Aha
Affiliations:
Department of Information and Computer Science, University of California, Irvine, Irvine, CA;The Turing Institute, Glasgow, Scotland
Venue:
AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2
Year:
1991

Citing 13
Cited 0

A theory of the learnable

Communications of the ACM
Toward memory-based reasoning

Communications of the ACM - Special issue on parallelism
Classifying learnable geometric concepts with the Vapnik-Chervonenkis dimension

STOC '86 Proceedings of the eighteenth annual ACM symposium on Theory of computing
On the learnability of Boolean formulae

STOC '87 Proceedings of the nineteenth annual ACM symposium on Theory of computing
Instance-based prediction of real-valued attributes

Computational Intelligence
Acquisition of dynamic control knowledge for a robotic manipulator

Proceedings of the seventh international conference (1990) on Machine learning
Incremental, instance-based learning of independent and graded concept descriptions

Proceedings of the sixth international workshop on Machine learning
Instance-Based Learning Algorithms

Machine Learning
Learning Decision Lists

Machine Learning
Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

Machine Learning
Learning From Noisy Examples

Machine Learning
Noise-tolerant instance-based learning algorithms

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Learning disjunction of conjunctions

IJCAI'85 Proceedings of the 9th international joint conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents PAC-learning analyses for instance-based learning algorithms for both symbolic and numeric-prediction tasks. The algorithms analyzed employ a variant of the k-nearest neighbor pattern classifier. The main results of these analyses are that the IB1 instance-based learning algorithm can learn, using a polynomial number of instances, a wide range of symbolic concepts and numeric functions. In. addition, we show that a bound on the degree of difficulty of predicting symbolic values may be obtained by considering the size of the boundary of the target concept, and a bound on the degree of difficulty in predicting numeric values may be obtained by considering the maximum absolute value of the slope between instances in the instance space. Moreover, the number of training instances required by IB1 is polynomial in these parameters. The implications of these results for the practical application of instance-based learning algorithms are discussed.