METHOD AND DEVICE FOR LEARNING NEURAL NETWORK

Title:

METHOD AND DEVICE FOR LEARNING NEURAL NETWORK

Document Type and Number:

Japanese Patent JP3303032

Kind Code:

B2

Abstract:

PURPOSE: To improve the versatility of the neural network in solving problems.
CONSTITUTION: The neural network is provided with a neural network arithmetic means 102 where some neurons are connected to multilayer (108, 109, and 110) and learning the relation between input and output signals with teacher signals 106 and 107 based on the learning algorithm, storing the learning result, and performing an arithmetic operation based on the learning result for input signals. The system is provided with a learning algorithm group 104 having several types of learning algorithm. From among several types of learning algorithm 1-n, algorithm to be used for the actual learning is designed to be selected by a learning algorithm selection means 105 according to the problems solved by the neural network arithmetic means 102. Thus, one neural network arithmetic means 102 can perform learning according to problems, resulting in improving versatility.

Inventors:

Masahiro Kayama
Shigeo Abe
Toshihiko Nakano

Application Number:

JP10677092A

Publication Date:

July 15, 2002

Filing Date:

April 24, 1992

Export Citation:

Click for automatic bibliography generation Help

Assignee:

株式会社日立製作所

International Classes:

G06F15/18; G06G7/60; G06N3/08; G06N99/00; (IPC1-7): G06N3/08

Domestic Patent References:

JP4215171A
JP395666A
JP451354A
JP561848A
JP4262453A

Other References:

ＮＥＵＲＯＳＩＭＴＭ／Ｌ−８６０使用者の手引き８７ＡＲ−０４９０−１，日本，富士通株式会社・発行，１９９２年１月３１日，初版，ｐｐ．８−１３，１９−２１，３１−３５，４５−５２，特許庁ＣＳＤＢ文献番号：ＣＳＮＺ１９９９００３４５００１
鹿山・他，「クラスタリング用ニューラルネットの学習方式」，情報処理学会第４４回（平成４年前期）全国大会講演論文集（第２分冊），日本，社団法人情報処理学会，１９９２年２月２４日，第２分冊，ｐｐ．２１５−２１６

Attorney, Agent or Firm:

Masami Akimoto

Previous Patent: 薄手スラブ連続注型プラントにおける注型チューブ供給・交換装置

Next Patent: MACHINE FOR AUTOMATICALLY POSITIONING AND ALIGNING CONTAINERS