Admissibility of Memorization Learning with Respect to Projection Learning in the Presence of Noise

摘要

In learning of feed-forward neural networks, so- called `training error' is often minimized. This is, however, not related to the generalization capability which is one of the ma- jor goals in the learning. It can be interpreted as a substitute for another learning which considers the generalization capabil- ity. Admissibility is a concept to discuss whether a learning can be a substitute for another learning. In this paper, we discuss the case where the learning which minimizes a training error is used as a substitute for the projection learning, which considers the generalization capability, in the presence of noise. Moreover, we give a method for choosing a training set which satisfies the admissibility.