Learning with Malicious Noise
Peter Auer
In: Encyclopedia of Algorithms (2008) Springer , pp. 1-99. ISBN 978-0-387-30770-1

This is the latest version of this eprint.

Abstract

This problem is concerned with PAC learning of concept classes when training examples are effected by malicious errors. The malicious noise model extends the PAC model by allowing example errors of any kind: it makes no assumptions on the nature of the errors that occur.

Available Versions of this Item

• Learning with Malicious Noise (deposited 13 February 2008)
  • Learning with Malicious Noise (deposited 24 March 2009) [Currently Displayed]

[Edit]