Title:
【発明の名称】ニューラル・ネットワークの評価方法
Document Type and Number:
Japanese Patent JP3132027
Kind Code:
B2
Abstract:
PURPOSE:To obtain a method for evaluating cause and effect relation between the input and output of a neural network. CONSTITUTION:The I/O functions of units in the neural network constituted of the hierarchical connection of units using respective neurons as models are developed by series and the network is expressed by a non-linear regression expression based upon the developed expression to attain the evaluation. Thus the cause and effect relation between the I/O of the neural network can be cleared by expressing the network by the non-linear regression expression.
Inventors:
Masahide Nomura
Hisanori Miyagaki
Eiji Toyama
Hisanori Miyagaki
Eiji Toyama
Application Number:
JP7000491A
Publication Date:
February 05, 2001
Filing Date:
April 02, 1991
Export Citation:
Assignee:
株式会社日立製作所
International Classes:
G06F15/18; G06G7/60; G06N3/04; G06N99/00; (IPC1-7): G06G7/60; G06F15/18
Other References:
【文献】電子情報通信学会技術報告 vol.90 no.280 1990年10月26日発行 p7~14、「汎関数級数表現における非線形システムの同定精度」横田康成 他2名 著
Attorney, Agent or Firm:
Yasuo Sakuta