DE69328596T2 - Optimierung eines Neuralnetzwerks mit Vorwärtskopplung - Google Patents

Optimierung eines Neuralnetzwerks mit Vorwärtskopplung

Info

Publication number
DE69328596T2
DE69328596T2 DE69328596T DE69328596T DE69328596T2 DE 69328596 T2 DE69328596 T2 DE 69328596T2 DE 69328596 T DE69328596 T DE 69328596T DE 69328596 T DE69328596 T DE 69328596T DE 69328596 T2 DE69328596 T2 DE 69328596T2
Authority
DE
Germany
Prior art keywords
feedforward
optimization
neural network
neural
network
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.)
Expired - Fee Related
Application number
DE69328596T
Other languages
English (en)
Other versions
DE69328596D1 (de
Inventor
John Mitchell
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi Europe Ltd
Original Assignee
Hitachi Europe 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 Hitachi Europe Ltd filed Critical Hitachi Europe Ltd
Publication of DE69328596D1 publication Critical patent/DE69328596D1/de
Application granted granted Critical
Publication of DE69328596T2 publication Critical patent/DE69328596T2/de
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
DE69328596T 1992-08-11 1993-07-29 Optimierung eines Neuralnetzwerks mit Vorwärtskopplung Expired - Fee Related DE69328596T2 (de)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
IE922575 1992-08-11

Publications (2)

Publication Number Publication Date
DE69328596D1 DE69328596D1 (de) 2000-06-15
DE69328596T2 true DE69328596T2 (de) 2001-01-04

Family

ID=11039732

Family Applications (1)

Application Number Title Priority Date Filing Date
DE69328596T Expired - Fee Related DE69328596T2 (de) 1992-08-11 1993-07-29 Optimierung eines Neuralnetzwerks mit Vorwärtskopplung

Country Status (3)

Country Link
EP (1) EP0583217B1 (de)
JP (1) JPH07302249A (de)
DE (1) DE69328596T2 (de)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7020595B1 (en) * 1999-11-26 2006-03-28 General Electric Company Methods and apparatus for model based diagnostics
MY138544A (en) 2003-06-26 2009-06-30 Neuramatix Sdn Bhd Neural networks with learning and expression capability
JP6948851B2 (ja) * 2016-06-30 2021-10-13 キヤノン株式会社 情報処理装置、情報処理方法
JP7047283B2 (ja) * 2017-08-24 2022-04-05 富士通株式会社 情報処理装置、方法、及びプログラム
JP6831347B2 (ja) * 2018-04-05 2021-02-17 日本電信電話株式会社 学習装置、学習方法および学習プログラム
CN110147873B (zh) * 2018-05-18 2020-02-18 中科寒武纪科技股份有限公司 卷积神经网络的处理器及训练方法
JP2022095999A (ja) * 2019-04-19 2022-06-29 国立大学法人北海道大学 ニューラル計算装置、および、ニューラル計算方法

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5093899A (en) * 1988-09-17 1992-03-03 Sony Corporation Neural network with normalized learning constant for high-speed stable learning
WO1991002315A1 (en) * 1989-08-01 1991-02-21 E.I. Du Pont De Nemours And Company Methods relating to the configuration of a parallel distributed processing network

Also Published As

Publication number Publication date
EP0583217A2 (de) 1994-02-16
EP0583217A3 (de) 1995-03-15
JPH07302249A (ja) 1995-11-14
DE69328596D1 (de) 2000-06-15
EP0583217B1 (de) 2000-05-10

Similar Documents

Publication Publication Date Title
DE69324052D1 (de) Neuronalnetzwerk-Lernsystem
DE69426278D1 (de) Kontinuierliche Herstellung eines Schlammes mit mehreren Komponenten
DE69400317T2 (de) Differentialprozessregelung mit künstlichen neuronalen Netzwerken
DE69300168T2 (de) Regelung eines Schienenfahrzeuges.
FR2714748B1 (fr) Apprentissage supervisé d'un réseau neuronique.
DE69421106T2 (de) Neuronales Netzwerk mit räumlich verteilter Arbeitsweise
DE69216077D1 (de) Praediktives selbst-organisierendes neuronales netzwerk
DE69321759T2 (de) Elektrostatischer Abscheider unter Verwendung eines Perlenbettes
EP0513638A3 (en) A fuzzy reasoning database question answering system
DE69128074D1 (de) Prozesssteuersystem und -verfahren mittels eines neuronalen Netzwerkes und/oder Expertensystems
DE69032576T2 (de) Dynamische Optimierung eines einzelnen relationalen Zugriffs
DE69533517D1 (de) Optimierung eines thermischen reaktors
DE69326436D1 (de) Kran ausgerüstet mit einem Wartungsaufzug
DE69228517D1 (de) Simulator mit Anwendung eines Neuronalnetzwerkes
ATA36793A (de) Elektroakustischer wandler mit einer maske
GB9024332D0 (en) Method of training a neural network
DE69531418D1 (de) Neuronales netzwerk mit reduzierter Berechnungsmenge
DE69328596D1 (de) Optimierung eines Neuralnetzwerks mit Vorwärtskopplung
GB2256737B (en) A learning system and a learning pattern showing method for a neural network
GB2267171B (en) Neural network employing absolute value calculating synapse
DE69126052T2 (de) Neuronales Netzwerk
DE69230422T2 (de) Neuronales Netzwerk und Lernverfahren
DE69231410D1 (de) Optimierung von Datenbanken
DE69225931T2 (de) Quantisierer mit neuronalem Netzwerk
GB9312600D0 (en) A method of regulating a continuous process,the method including an optimization stage and a regualtion stage

Legal Events

Date Code Title Description
8364 No opposition during term of opposition
8339 Ceased/non-payment of the annual fee