For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Incremental Construction of Projection Generalizing Neural Networks
Masashi SUGIYAMA Hidemitsu OGAWA
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2002/09/01
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Biocybernetics, Neurocomputing
generalization capability, incremental learning, pseudo biorthogonal basis (PBOB), projection learning, projection generalizing neural network,
Full Text: PDF>>
In many practical situations in NN learning, training examples tend to be supplied one by one. In such situations, incremental learning seems more natural than batch learning in view of the learning methods of human beings. In this paper, we propose an incremental learning method in neural networks under the projection learning criterion. Although projection learning is a linear learning method, achieving the above goal is not straightforward since it involves redundant expressions of functions with over-complete bases, which is essentially related to pseudo biorthogonal bases (or frames). The proposed method provides exactly the same learning result as that obtained by batch learning. It is theoretically shown that the proposed method is more efficient in computation than batch learning.