NeuroCOLT

Neural Networks and Computational Learning Theory

 

About NeuroCOLT

Papers Archive

1994 1995
1996 1997
1998 1999
2000 2001

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-98-005


Query, PACS and simple-PAC Learning


Jorge Castro & David Guijarro
UPC
Barcelona

Keywords: learning, distribution-dependent, PAC, PACS,Kolmogorov complexity

Received: 16-FEB-1998


Abstract
We study a distribution-dependent form of PAC learning that uses probability distributions related to Kolmogorov complexity. We relate the PACS model, defined by Denis, D'Halluin and Gilleron in~\cite{dhg}, with the standard simple-PAC model and give a general technique that subsumes the results in Denis, D'Halluin and Gilleron (1996) and Parekh and Honavar (1997).

Download Compressed Postscript