PAC Learning with Simple Examples - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 1996

PAC Learning with Simple Examples

Abstract

We define a new PAC learning model. In this model, examples are drawn according to the universal distribution m(. ¦ f) of Solomomoff-Levin, where f is the target concept. The consequence is that the simple examples of the target concept have a high probability to be provided to the learning algorithm. We prove an Occam's Razor theorem. We show that the class of poly-term DNF is learnable, and the class of k-reversible languages is learnable from positive data, in this new model.
No file

Dates and versions

inria-00538883 , version 1 (23-11-2010)

Identifiers

  • HAL Id : inria-00538883 , version 1

Cite

François Denis, Cyrille Dhalluin, Rémi Gilleron. PAC Learning with Simple Examples. 13th Annual Symposium on Theoretical Aspects of Computer Science, STACS'96, 1996, Munich, France. pp.231--242. ⟨inria-00538883⟩
110 View
0 Download

Share

Gmail Facebook X LinkedIn More