Sciweavers

PAKDD
2000
ACM
100views Data Mining» more  PAKDD 2000»
14 years 4 months ago
Discovery of Relevant Weights by Minimizing Cross-Validation Error
In order to discover relevant weights of neural networks, this paper proposes a novel method to learn a distinct squared penalty factor for each weight as a minimization problem ov...
Kazumi Saito, Ryohei Nakano