How to design a regularization term for improving generalization
説明
In supervised learning, the regularization method is often used for improving the level of generalization. We give a necessary and sufficient condition of an optimal regularization term, i.e., a regularization operator and parameter. The optimality is discussed based on the projection learning criterion in which the minimization of a generalization error is explicitly considered. We suggest how to design the optimal regularization term so as to satisfy the obtained condition.
収録刊行物
-
- ICONIP'99. ANZIIS'99 & ANNES'99 & ACNN'99. 6th International Conference on Neural Information Processing. Proceedings (Cat. No.99EX378)
-
ICONIP'99. ANZIIS'99 & ANNES'99 & ACNN'99. 6th International Conference on Neural Information Processing. Proceedings (Cat. No.99EX378) 1 222-227, 2003-01-22
IEEE
