Inductive learning from good examples

Authors:
Xiaofeng Ling
Affiliations:
Department of Computer Science, University of Western Ontario, London, Ontario, Canada
Venue:
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
Year:
1991

Citing 10
Cited 2

A theory of the learnable

Communications of the ACM
Artificial intelligence (2nd ed.)

Artificial intelligence (2nd ed.)
Generalized subsumption and its applications to induction and redundancy

Artificial Intelligence
Model inference incorporating generalization

Journal of Information Processing
Learnability and the Vapnik-Chervonenkis dimension

Journal of the ACM (JACM)
Learning complicated concepts reliably and usefully

COLT '88 Proceedings of the first annual workshop on Computational learning theory
Learning theories in a subset of a polyadic logic

COLT '88 Proceedings of the first annual workshop on Computational learning theory
Queries and Concept Learning

Machine Learning
Queries and Concept Learning

Machine Learning
Inductive Inference from Good Examples

AII '89 Proceedings of the International Workshop on Analogical and Inductive Inference

Learning recursive functions: A survey

Theoretical Computer Science
Refinement of uncertain rule bases via reduction

International Journal of Approximate Reasoning

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study what kind of data may ease the computational complexity of learning of Horn clause theories (in Gold's paradigm) and Boolean functions (in PAC-learning paradigm). We give several definitions of good data (basic and generative representative sets), and develop data-driven algorithms that learn faster from good examples, and degenerate to learn in the limit from the "worst" possible examples. We show that Horn clause theories, k-term DNF and general DNF Boolean functions are polynomially learnable from generative representative presentations.