A Compact Structuring Method for Hierarchical Neural Networks by Eliminating Extra Hidden Layers and Units

DOI Web Site Web Site 1 Citations Open Access

Bibliographic Information

Other Title
  • 冗長な隠れ層・隠れユニットの削除による階層型ニューラルネットのコンパクト構造化
  • ジョウチョウ ナ カクレソウ カクレ ユニット ノ サクジョ ニ ヨル カイソ

Search this article

Description

When we apply a hierarchical neural network based on the back-propagation algorithm to a particular problem, we must determine beforehand the suitable size of network for the problem. But it is a very difficult problem. Too small a network will not learn at all, while too large a network will be inefficient and worsen its generalization ability due to overfitting.<br>In order to solve this problem, in this paper we propose a compact structuring method based on learning with a large size network and then compacting gradually the network by eliminating extra hidden layers and units. The result is a small and efficient network that performs better than the original. Also we demonstrate the effectiveness of this method by appling it to an identification problem of logic function.

Journal

Citations (1)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top