DE112013002897A5 - Verfahren zum Trainieren eines künstlichen neuronalen Netzes - Google Patents

Verfahren zum Trainieren eines künstlichen neuronalen Netzes Download PDF

Info

Publication number
DE112013002897A5
DE112013002897A5 DE112013002897.2T DE112013002897T DE112013002897A5 DE 112013002897 A5 DE112013002897 A5 DE 112013002897A5 DE 112013002897 T DE112013002897 T DE 112013002897T DE 112013002897 A5 DE112013002897 A5 DE 112013002897A5
Authority
DE
Germany
Prior art keywords
training
neural network
artificial neural
artificial
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.)
Withdrawn
Application number
DE112013002897.2T
Other languages
English (en)
Inventor
Gerhard Döding
László Germán
Klaus Kemper
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.)
KISTERS AG
Original Assignee
KISTERS AG
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 KISTERS AG filed Critical KISTERS AG
Publication of DE112013002897A5 publication Critical patent/DE112013002897A5/de
Withdrawn legal-status Critical Current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
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Feedback Control In General (AREA)
DE112013002897.2T 2012-05-14 2013-04-17 Verfahren zum Trainieren eines künstlichen neuronalen Netzes Withdrawn DE112013002897A5 (de)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201261688433P 2012-05-14 2012-05-14
DE102012009502.3 2012-05-14
DE102012009502A DE102012009502A1 (de) 2012-05-14 2012-05-14 Verfahren zum Trainieren eines künstlichen neuronalen Netzes
US61/688,433 2012-05-14
PCT/DE2013/000197 WO2013170843A1 (de) 2012-05-14 2013-04-17 Verfahren zum trainieren eines künstlichen neuronalen netzes

Publications (1)

Publication Number Publication Date
DE112013002897A5 true DE112013002897A5 (de) 2015-02-26

Family

ID=49475318

Family Applications (2)

Application Number Title Priority Date Filing Date
DE102012009502A Withdrawn DE102012009502A1 (de) 2012-05-14 2012-05-14 Verfahren zum Trainieren eines künstlichen neuronalen Netzes
DE112013002897.2T Withdrawn DE112013002897A5 (de) 2012-05-14 2013-04-17 Verfahren zum Trainieren eines künstlichen neuronalen Netzes

Family Applications Before (1)

Application Number Title Priority Date Filing Date
DE102012009502A Withdrawn DE102012009502A1 (de) 2012-05-14 2012-05-14 Verfahren zum Trainieren eines künstlichen neuronalen Netzes

Country Status (3)

Country Link
US (1) US20150134581A1 (de)
DE (2) DE102012009502A1 (de)
WO (1) WO2013170843A1 (de)

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104217260B (zh) * 2014-09-19 2017-08-22 南京信息工程大学 一种风场邻近多台风电机测量风速缺损值的组合填充系统
US20170364799A1 (en) * 2016-06-15 2017-12-21 Kneron Inc. Simplifying apparatus and simplifying method for neural network
US11437032B2 (en) 2017-09-29 2022-09-06 Shanghai Cambricon Information Technology Co., Ltd Image processing apparatus and method
US11169803B2 (en) 2018-02-13 2021-11-09 Shanghai Cambricon Information Technology Co., Ltd. Computing device and method
US11630666B2 (en) 2018-02-13 2023-04-18 Shanghai Cambricon Information Technology Co., Ltd Computing device and method
EP3617959B1 (de) 2018-02-13 2021-08-04 Shanghai Cambricon Information Technology Co., Ltd Rechenvorrichtung und -verfahren
CN116991225A (zh) 2018-02-14 2023-11-03 上海寒武纪信息科技有限公司 处理器的控制装置、方法及设备
EP3624020A4 (de) * 2018-05-18 2021-05-05 Shanghai Cambricon Information Technology Co., Ltd Berechnungsverfahren und zugehöriges produkte
EP3798850A4 (de) 2018-06-27 2022-03-23 Shanghai Cambricon Information Technology Co., Ltd Verfahren, vorrichtung und system zur fehlerbeseitigung in einem chip
WO2020042739A1 (zh) 2018-08-28 2020-03-05 中科寒武纪科技股份有限公司 数据预处理方法、装置、计算机设备和存储介质
WO2020062392A1 (zh) 2018-09-28 2020-04-02 上海寒武纪信息科技有限公司 信号处理装置、信号处理方法及相关产品
US11922314B1 (en) * 2018-11-30 2024-03-05 Ansys, Inc. Systems and methods for building dynamic reduced order physical models
CN111383638A (zh) 2018-12-28 2020-07-07 上海寒武纪信息科技有限公司 信号处理装置、信号处理方法及相关产品
US20200334522A1 (en) 2019-04-18 2020-10-22 Cambricon Technologies Corporation Limited Data processing method and related products
CN111832738B (zh) 2019-04-18 2024-01-09 中科寒武纪科技股份有限公司 一种数据处理方法及相关产品
CN112085186B (zh) 2019-06-12 2024-03-05 上海寒武纪信息科技有限公司 一种神经网络的量化参数确定方法及相关产品
US11676029B2 (en) 2019-06-12 2023-06-13 Shanghai Cambricon Information Technology Co., Ltd Neural network quantization parameter determination method and related products
WO2021036904A1 (zh) 2019-08-23 2021-03-04 安徽寒武纪信息科技有限公司 数据处理方法、装置、计算机设备和存储介质
US11514326B2 (en) * 2020-06-18 2022-11-29 International Business Machines Corporation Drift regularization to counteract variation in drift coefficients for analog accelerators

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2648251B1 (fr) * 1989-06-09 1991-09-13 Labo Electronique Physique Methode d'apprentissage et structure de reseau de neurones

Also Published As

Publication number Publication date
WO2013170843A1 (de) 2013-11-21
DE102012009502A1 (de) 2013-11-14
US20150134581A1 (en) 2015-05-14

Similar Documents

Publication Publication Date Title
DE112013002897A5 (de) Verfahren zum Trainieren eines künstlichen neuronalen Netzes
GB201402736D0 (en) Method of training a neural network
EP2885745A4 (de) Vorrichtung und verfahren für lernvorgänge in einem neuronalen spiking-netzwerk
DE112013001553A5 (de) Optoelektronisches Bauelement und Verfahren zum Herstellen eines optoelektronischen Bauelements
HK1199672A1 (en) Method and apparatus for acoustic model training
DK2906353T3 (da) Fremgangsmåde og apparat til elektrostatisk maling
PL2996467T3 (pl) Urządzenie i sposób do odstraszania ptaków za pomocą lasera
EP2911504A4 (de) Vorrichtung und verfahren zur hundeerziehung
DE112013004449T8 (de) Vorrichtung und Verfahren zum Optimieren von halbaktiven Auslastungen
CO6852026A2 (es) Simulador de entrenamiento y métodos relacionados
IL226878A0 (en) A computerized audio-feedback system and method for eye practice controlled by an operator
BR112014013919A2 (pt) aparelho e método de desaeração
DE102014102565A8 (de) Optoelektronisches Bauelement und Verfahren zum Herstellen eines optoelektronischen Bauelements
DE112013001133A5 (de) Verfahren zum Herstellen eines optoelektronischen Bauelements und derart hergestelltes optoelektronisches Bauelement
DE112013000239A5 (de) Verfahren und Vorrichtung zur Herstellung eines Seils
DE102014119627A8 (de) Verfahren zum Erzeugen eines holografisch-optischen Strahlformungselements
BR112014018277A2 (pt) aparelho de previsão do tempo e método de previsão do tempo
DE112012006658A5 (de) Verfahren zum Entriegeln eines Steckers
DE112012001960A5 (de) Verfahren und System zum Lokalisieren einer Person
BR112013032680A2 (pt) método e aparelho de pós-formagem
LU91878B1 (de) Verfahren und Vorrichtung zum Wurftraining
BR112015009302A2 (pt) método de aplicação de um marcador radiopaco e aparelho
DE112015000738A5 (de) Verfahren zur Übertragung eines Datenstroms in Echtzeit
DE112014002223A5 (de) Verfahren zum Betreiben eines LED-Konverters
GB2500994B (en) Apparatus and method for aiding learning

Legal Events

Date Code Title Description
R082 Change of representative

Representative=s name: PATENTANWALTSKANZLEI LIERMANN-CASTELL, DE

R082 Change of representative
R119 Application deemed withdrawn, or ip right lapsed, due to non-payment of renewal fee