article · 1997
Limitations On Inductive Learning
Exte Nd Ed, Thomas G. Dietterich
Cited by 0Abstract and details only
Abstract
) Thomas G. Dietterich Department of Computer Science Oregon State University Corvallis, OR 97331 tgd@cs.orst.edu ABSTRACT This paper explores the proposition that inductive learning from examples is fundamentally limited to learning only a small fraction of the total space of possible hypotheses. We begin by defining the notion of an algorithm reliably learning a good approximation to a concept C. An empirical study of three algorithms (the classical algorithm for maximally specific conjunctive generalizations, ID3, and back-propagation for feed-forward networks of logistic units) demonstrates that each of these algorithms performs very poorly for the task of learning concepts defined over the space of Boolean feature vectors containing 3 variables. Simple counting arguments allow us to prove an upper bound on the maximum number of concepts reliably learnable from m training examples. INTRODUCTION How good are current inductive learning algorithms? How well can any inductive ...
Cite this paper
Ed, E. N., & Dietterich, T. G. (1997). Limitations On Inductive Learning.
Ed, Exte Nd, and Thomas G. Dietterich. “Limitations On Inductive Learning.” 1997.
Ed, Exte Nd, and Thomas G. Dietterich. 1997. “Limitations On Inductive Learning.”
Ed, E.N. and Dietterich, T.G. (1997) ‘Limitations On Inductive Learning’.
@article{ed1997limitations,
title = {{Limitations On Inductive Learning}},
author = {Ed, Exte Nd and Dietterich, Thomas G.},
year = {1997}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.