@article{oai:fukuyama-u.repo.nii.ac.jp:00007967,
 author = {渡辺, 栄治},
 issue = {2},
 journal = {福山大学工学部紀要},
 month = {Mar},
 note = {P(論文), This paper discusses the relation between internal representations and generalization ability of multi-layered neural networks for function approximation problems. Here, the over learning problem, which makes the generalization ability poor, is divided into the two problems; the excessive degrees of freedom and the non-uniqueness of weights. These problems are carefully discussed from the viewpoint of internal representation; weights and outputs of hidden units. First, the excessive degrees of freedom problem is discussed by introducing the entropy for weights. Next, the non-uniqueness of weights problem is also discussed by introducing the principal components analysis method. Finally, the relations between internal representations and generalization ability of multi-layered neural networks are concretely discussed by numerical results.},
 pages = {37--44},
 title = {関数近似問題に対する階層型ニューラルネットワークの内部表現と汎化能力の関係},
 volume = {19},
 year = {1996}
}