Query , PACS and simple - PACLearning 1

Abstract

We study a distribution dependent form of PAC learning that uses probability distributions related to Kolmogorov complexity. We relate the PACS model, deened by Denis, D'Halluin and Gilleron in 3], with the standard simple-PAC model and give a general technique that subsumes the results in 3] and 6].

Cite this paper

@inproceedings{Castro1998QueryP, title={Query , PACS and simple - PACLearning 1}, author={Jorge Castro and David GuijarroDept}, year={1998} }