General Inductive Inference Types Based on Linearly-Ordered Sets

摘要

In this paper, we reconsider the definitions of procrastinating learning machines. In the original definition of Freivalds and Smith, constructive ordinals are used to bound mindchanges. We investigate the possibility of using arbitrary linearly ordered sets to bound mindchanges in a similar way. It turns out that using certain ordered sets it is possible to define inductive inference types more general than the previously known ones. We investigate properites of the new inductive inference types and compare them to other types.