JPH0464134A - Learning method for neural unit with fully coupled rule part - Google Patents

Learning method for neural unit with fully coupled rule part

Info

Publication number
JPH0464134A
JPH0464134A JP2174608A JP17460890A JPH0464134A JP H0464134 A JPH0464134 A JP H0464134A JP 2174608 A JP2174608 A JP 2174608A JP 17460890 A JP17460890 A JP 17460890A JP H0464134 A JPH0464134 A JP H0464134A
Authority
JP
Japan
Prior art keywords
learning
rule
membership function
function realizing
antecedent
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP2174608A
Other languages
Japanese (ja)
Inventor
Kazuo Asakawa
Akira Kawamura
Ryusuke Masuoka
Shigenori Matsuoka
Hiroyuki Okada
Arimichi Oowada
Nobuo Watabe
Original Assignee
Fuji Facom Corp
Fujitsu Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fuji Facom Corp, Fujitsu Ltd filed Critical Fuji Facom Corp
Priority to JP2174608A priority Critical patent/JPH0464134A/en
Publication of JPH0464134A publication Critical patent/JPH0464134A/en
Pending legal-status Critical Current

Links

Abstract

PURPOSE: To improve the efficiency of learning by initializing a weight value and a threshold value at each of an antecedent part membership function realizing part, rule part, and consequent part membership function realizing part, and then simultaneously learning the antecedent part membership function realizing part and the rule part after learning the rule part.
CONSTITUTION: The weight value and the threshold value based on knowledge stored preliminarily or based on random numbers are initialized at each of an antecedent part membership function realizing part 10, rule part 12, and consequent part membership function realizing part 14. Then, the weights of the antecedent membership function realizing part 10 and the rule part 12 are simultaneously learned after learning the weight of the rule part 12 using a learning data prepared preliminarily. Thus, the learning to operate a control suited to an object system can be realized efficiently.
COPYRIGHT: (C)1992,JPO&Japio
JP2174608A 1990-07-03 1990-07-03 Learning method for neural unit with fully coupled rule part Pending JPH0464134A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2174608A JPH0464134A (en) 1990-07-03 1990-07-03 Learning method for neural unit with fully coupled rule part

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2174608A JPH0464134A (en) 1990-07-03 1990-07-03 Learning method for neural unit with fully coupled rule part

Publications (1)

Publication Number Publication Date
JPH0464134A true JPH0464134A (en) 1992-02-28

Family

ID=15981564

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2174608A Pending JPH0464134A (en) 1990-07-03 1990-07-03 Learning method for neural unit with fully coupled rule part

Country Status (1)

Country Link
JP (1) JPH0464134A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008296572A (en) * 2007-05-29 2008-12-11 Samsung Electronics Co Ltd Inkjet printhead and method for manufacturing the same
JP2010503236A (en) * 2006-09-06 2010-01-28 東京エレクトロン株式会社 Substrate cleaning method and substrate cleaning apparatus

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010503236A (en) * 2006-09-06 2010-01-28 東京エレクトロン株式会社 Substrate cleaning method and substrate cleaning apparatus
JP4874394B2 (en) * 2006-09-06 2012-02-15 東京エレクトロン株式会社 Substrate cleaning method and substrate cleaning apparatus
JP2008296572A (en) * 2007-05-29 2008-12-11 Samsung Electronics Co Ltd Inkjet printhead and method for manufacturing the same

Similar Documents

Publication Publication Date Title
CA2105842A1 (en) Neural Network Based Control System
JPH0310366A (en) Artificial neural network
JPH04305760A (en) Reception field neural network executing recognition of shift/invariant pattern
JPH03127185A (en) Point pattern matching method
JPH04266153A (en) Neural network
JPH04157559A (en) Neural network
JPH03296880A (en) Learning method for neural network
JPH0464134A (en) Learning method for neural unit with fully coupled rule part
JPH0464133A (en) Learning method for neural unit with fully coupled rule part
JPH0464136A (en) Learning method for neural unit with fully coupled rule part
JPH0464137A (en) Learning method for neural unit with fully coupled rule part
JPH0464135A (en) Learning method for neural unit with fully coupled rule part
JPH0464132A (en) Learning method for neural unit with fully coupled rule part
JPH02260002A (en) Fuzzy controller
JPH0424741A (en) Learning method for prewired neuro of rule part
JPH0424740A (en) Learning method for prewired neuro of rule part
JPH04275633A (en) Construction system for membership function by neural network
JPH0424738A (en) Learning method for prewired neuro of rule part
JPH04220758A (en) Time sequence data prediction and prediction recognition method
JPH0424739A (en) Learning method for prewired neuro of rule part
JPH04275634A (en) Construction system for membership function by neural network
JPH04142628A (en) Composite rule learning system
JPH0424737A (en) Learning method for prewired neuro of rule part
JPH04186402A (en) Learning system in fuzzy inference
JPH02260041A (en) Fuzzy multistage inference device