Computational learning theory: new models and algorithms

@inproceedings{Sloan1989ComputationalLT,
  title={Computational learning theory: new models and algorithms},
  author={Robert H. Sloan},
  year={1989}
}
In the past several years, there has been a surge of interest in computational learning theory-the formal (as opposed to empirical) study of learning algorithms. One major cause for this interest was the model of probably approximately correct learning, or pac learning, introduced by Valiant in 1984. This thesis begins by presenting a new learning algorithm for a particular problem within that model: learning submodules of the free Z-module Zk. We prove that this algorithm achieves probable… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 52 references

The Minimum Consistent DFA Problem Cannot be Approximated within any Polynomial (abstract)

Structure in Complexity Theory Conference • 1989
View 5 Excerpts
Highly Influenced

Inference of Reversible Languages

J. ACM • 1982
View 8 Excerpts
Highly Influenced

Learning from Good and Bad Data. Kluwer international series in engineering and computer science

Philip D. Laird
1988
View 6 Excerpts
Highly Influenced

Learning from noisy examples

Machine Learning • 1987
View 8 Excerpts
Highly Influenced

Occam's Razor

View 4 Excerpts
Highly Influenced

A Theory of the Learnable

STOC • 1984
View 15 Excerpts
Highly Influenced

Theory and application of trapdoor functions

23rd Annual Symposium on Foundations of Computer Science (sfcs 1982) • 1982
View 5 Excerpts
Highly Influenced

How to construct random functions

View 4 Excerpts
Highly Influenced

The effect of noise on concept learning

J. Ross Quinlan
Machine Learning, An Artificial Intelligence Approach (Volume II), chapter 6, pages 149-166, Morgan Kaufmann, • 1986
View 3 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…