A New Learning Method Using Prior Information of Neural Networks

DOI HANDLE オープンアクセス
  • 呂 栢権
    九州大学ベンチャービジネスラボラトリー
  • 平澤 宏太郎
    九州大学大学院システム情報科学研究科電気電子システム工学専攻
  • 村田 純一
    九州大学大学院システム情報科学研究科電気電子システム工学専攻
  • 胡 敬炉
    九州大学大学院システム情報科学研究科電気電子システム工学専攻

この論文をさがす

抄録

In this paper, we present a new learning method using prior information for three-layer neural networks. Usually when neural networks are used for identification of systems, all of their weights are trained independently, without considering their inter-relation of weights values. Thus the training results are not usually good. The reason for this is that each parameter has its influence on others during the learning. To overcome this problem, first, we give exact mathematical equation that describes the relation between weight values given a set of data conveying prior information. Then we present a new learning method that trains the part of the weights and calculates the others by using these exact mathematical equations. This method often keeps a priori given mathematical structure exactly during the learning, in other words, training is done so that the network follows predetermined trajectory. Numerical computer simulation results are provided to support the present approaches.

収録刊行物

詳細情報 詳細情報について

  • CRID
    1390290699820225024
  • NII論文ID
    110000579904
  • NII書誌ID
    AN10569524
  • DOI
    10.15017/1498417
  • ISSN
    21880891
    13423819
  • HANDLE
    2324/1498417
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • IRDB
    • CiNii Articles
  • 抄録ライセンスフラグ
    使用可

問題の指摘

ページトップへ