Papers
www.cs.dartmouth.edu/~sws/abstracts/fjs91.shtml
Last modified: 08/27/03 11:56:51 AM

M. Furst, J. Jackson, S. Smith.
``Improved Learning of AC0 Functions.''
4th Annual Workshop on Computational Learning Theory.
1991.

Abstract

Two extensions of the Linial, Mansour, Nisan AC0 learning algorithm are presented. The LMN method works when input examples are drawn uniformly. The new algorithms improve on theirs by performing well when given inputs drawn from unknown, mutually independent distributions. A variant of the one of the algorithms is conjectured to work in an even broader setting.

Download

PDF

Back to home page Maintained by Sean Smith, sws@cs.dartmouth.edu