Considerations of Learnability of Multilayer Neural Networks

スポンサーリンク

概要

• 論文の詳細を見る

• This letter describes the concepts that the learnability of multilayer neural networks exists in a constrained hypersurface in learning space which is formed by input and output subspace of multilayer neural networks, and that a priori information, providing constraints on the learning space, is required for generalization.

• 社団法人電子情報通信学会の論文
• 1993-02-25

著者

• Itoh Yasuo

  S

関連論文

• Considerations of Learnability of Multilayer Neural Networks

スポンサーリンク