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

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

Akira HIRABAYASHI  Hidemitsu OGAWA  Yukihiko YAMASHITA

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E82-D   No.2   pp.488-496
Publication Date: 1999/02/25
Online ISSN:
DOI:
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Bio-Cybernetics and Neurocomputing
Keyword:
feedforward neural network,  generalization,  training error,  over-learning,  admissibility,

Full Text: PDF>>

Summary:
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 major goals in the learning. It can be interpreted as a substitute for another learning which considers the generalization capability. 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.