EP3469521A4 - Neural network and method of neural network training - Google Patents

Neural network and method of neural network training Download PDF

Info

Publication number: EP3469521A4
Authority: EP; European Patent Office
Prior art keywords: neural network; training; network training; neural; network
Prior art date: 2016-06-09
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 Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.): Withdrawn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

EP17811082.1A

Other languages

German (de)

French (fr)

Other versions

EP3469521A1 (en

Inventor

Dmitri PESCIANSCHI

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.)

Progress Inc

Original Assignee

Progress Inc

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.)

2016-06-09

Filing date

2017-06-09

Publication date

2020-02-26

2016-06-09 Priority claimed from US15/178,137 external-priority patent/US9619749B2/en

2017-03-03 Priority claimed from US15/449,614 external-priority patent/US10423694B2/en

2017-06-09 Application filed by Progress Inc filed Critical Progress Inc

2019-04-17 Publication of EP3469521A1 publication Critical patent/EP3469521A1/en

2020-02-26 Publication of EP3469521A4 publication Critical patent/EP3469521A4/en

Status Withdrawn legal-status Critical Current

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
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
- G06N3/065—Analogue means
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks

Landscapes

Engineering & Computer Science (AREA)
Physics & Mathematics (AREA)
Theoretical Computer Science (AREA)
Health & Medical Sciences (AREA)
Life Sciences & Earth Sciences (AREA)
Biomedical Technology (AREA)
Biophysics (AREA)
Software Systems (AREA)
Evolutionary Computation (AREA)
General Physics & Mathematics (AREA)
Artificial Intelligence (AREA)
Mathematical Physics (AREA)
Data Mining & Analysis (AREA)
Computing Systems (AREA)
General Engineering & Computer Science (AREA)
Molecular Biology (AREA)
General Health & Medical Sciences (AREA)
Computational Linguistics (AREA)
Neurology (AREA)
Image Analysis (AREA)
Computer Vision & Pattern Recognition (AREA)
Medical Informatics (AREA)

EP17811082.1A 2016-06-09 2017-06-09 Neural network and method of neural network training Withdrawn EP3469521A4 (en)

Applications Claiming Priority (3)

Application Number	Priority Date	Filing Date	Title
US15/178,137 US9619749B2 (en)	2014-03-06	2016-06-09	Neural network and method of neural network training
US15/449,614 US10423694B2 (en)	2014-03-06	2017-03-03	Neural network and method of neural network training
PCT/US2017/036758 WO2017214507A1 (en)	2016-06-09	2017-06-09	Neural network and method of neural network training

Publications (2)

Publication Number	Publication Date
EP3469521A1 EP3469521A1 (en)	2019-04-17
EP3469521A4 true EP3469521A4 (en)	2020-02-26

Family

ID=60579026

Family Applications (1)

Application Number	Title	Priority Date	Filing Date
EP17811082.1A Withdrawn EP3469521A4 (en)	2016-06-09	2017-06-09	Neural network and method of neural network training

Country Status (5)

Country	Link
EP (1)	EP3469521A4 (en)
JP (1)	JP7041078B2 (en)
KR (1)	KR102558300B1 (en)
CN (1)	CN109416758A (en)
WO (1)	WO2017214507A1 (en)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number	Priority date	Publication date	Assignee	Title
DE102018202095A1 (en) *	2018-02-12	2019-08-14	Robert Bosch Gmbh	Method and apparatus for checking neuron function in a neural network
US11454968B2 (en) *	2018-02-28	2022-09-27	Micron Technology, Inc.	Artificial neural network integrity verification
US11562231B2 (en) *	2018-09-03	2023-01-24	Tesla, Inc.	Neural networks for embedded devices
US11640522B2 (en)	2018-12-13	2023-05-02	Tybalt, Llc	Computational efficiency improvements for artificial neural networks
CN109799439B (en) *	2019-03-29	2021-04-13	云南电网有限责任公司电力科学研究院	Insulating multi-angle inclined scratch cable wetting experiment evaluation method and device
CN110111234B (en) *	2019-04-11	2023-12-15	上海集成电路研发中心有限公司	Image processing system architecture based on neural network
CN110135557B (en) *	2019-04-11	2023-06-02	上海集成电路研发中心有限公司	Neural network topology architecture of image processing system
CN110046513B (en) *	2019-04-11	2023-01-03	长安大学	Plaintext associated image encryption method based on Hopfield chaotic neural network
KR102675806B1 (en)	2019-05-03	2024-06-18	삼성전자주식회사	Image processing apparatus and image processing method thereof
US11361218B2 (en) *	2019-05-31	2022-06-14	International Business Machines Corporation	Noise and signal management for RPU array
US11714999B2 (en) *	2019-11-15	2023-08-01	International Business Machines Corporation	Neuromorphic device with crossbar array structure storing both weights and neuronal states of neural networks
KR102410166B1 (en) *	2019-11-27	2022-06-20	고려대학교 산학협력단	Deep neural network accelerator using heterogeneous multiply-accumulate unit
CN111461308B (en) *	2020-04-14	2023-06-30	中国人民解放军国防科技大学	Memristor neural network and weight training method
JP7493398B2 (en)	2020-07-03	2024-05-31	日本放送協会	Conversion device, learning device, and program
CN111815640B (en) *	2020-07-21	2022-05-03	江苏经贸职业技术学院	Memristor-based RBF neural network medical image segmentation algorithm
CN112215344A (en) *	2020-09-30	2021-01-12	清华大学	Correction method and design method of neural network circuit
US20220138579A1 (en) *	2020-11-02	2022-05-05	International Business Machines Corporation	Weight repetition on rpu crossbar arrays
CN113570048B (en) *	2021-06-17	2022-05-31	南方科技大学	Circuit simulation-based memristor array neural network construction and optimization method
KR102514652B1 (en) *	2021-11-19	2023-03-29	서울대학교산학협력단	Weight transfer apparatus for neuromorphic devices and weight transfer method using the same
CN115358389B (en) *	2022-09-01	2024-08-20	清华大学	Training error reduction method and device for neural network, electronic equipment and medium
WO2024206841A1 (en) *	2023-03-31	2024-10-03	President And Fellows Of Harvard College	Systems and methods for differentiable optical processors

Citations (2)

* Cited by examiner, † Cited by third party
Publication number	Priority date	Publication date	Assignee	Title
US5600843A (en) *	1989-09-20	1997-02-04	Fujitsu Limited	Ring systolic array system for synchronously performing matrix/neuron computation using data transferred through cyclic shift register connected in cascade of trays
US20160012330A1 (en) *	2014-03-06	2016-01-14	Progress, Inc.	Neural network and method of neural network training

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number	Priority date	Publication date	Assignee	Title
CN101980290B (en) *	2010-10-29	2012-06-20	西安电子科技大学	Method for fusing multi-focus images in anti-noise environment
US10095718B2 (en) *	2013-10-16	2018-10-09	University Of Tennessee Research Foundation	Method and apparatus for constructing a dynamic adaptive neural network array (DANNA)

2017
- 2017-06-09 WO PCT/US2017/036758 patent/WO2017214507A1/en unknown
- 2017-06-09 EP EP17811082.1A patent/EP3469521A4/en not_active Withdrawn
- 2017-06-09 CN CN201780035716.7A patent/CN109416758A/en active Pending
- 2017-06-09 JP JP2018564317A patent/JP7041078B2/en active Active
- 2017-06-09 KR KR1020197000226A patent/KR102558300B1/en active IP Right Grant

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number	Priority date	Publication date	Assignee	Title
US5600843A (en) *	1989-09-20	1997-02-04	Fujitsu Limited	Ring systolic array system for synchronously performing matrix/neuron computation using data transferred through cyclic shift register connected in cascade of trays
US20160012330A1 (en) *	2014-03-06	2016-01-14	Progress, Inc.	Neural network and method of neural network training

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
DMITRI PESCIANSCHI ET AL: "Analog and Digital Modeling of a Scalable Neural Network", PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (ICAI 2015), vol. II, 27 July 2015 (2015-07-27), XP055658955 *
DMITRI PESCIANSCHI ET AL: "Main Principles of the General Theory of Neural Network with Internal Feedback Neural Network", PROCEEDINGS OF THE 2015 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (ICAI 2015), vol. II, 27 July 2015 (2015-07-27), XP055658960 *
See also references of WO2017214507A1 *
YU-YI LIAO ET AL: "CMAC WITH CLUSTERING MEMORY AND ITS APPLICATION TO FACIAL EXPRESSION RECOGNITION", INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE (IJPRAI), WORLD SCIENTIFIC PUBLISHING, SI, vol. 25, no. 7, 1 November 2011 (2011-11-01), pages 1055 - 1072, XP001570451, ISSN: 0218-0014, DOI: 10.1142/S0218001411008968 *

Also Published As

Publication number	Publication date
WO2017214507A1 (en)	2017-12-14
EP3469521A1 (en)	2019-04-17
KR20190016539A (en)	2019-02-18
CN109416758A (en)	2019-03-01
JP2019519045A (en)	2019-07-04
KR102558300B1 (en)	2023-07-21
JP7041078B2 (en)	2022-03-23

Publication	Publication Date	Title
EP3469521A4 (en)	2020-02-26	Neural network and method of neural network training
EP3114540A4 (en)	2017-11-08	Neural network and method of neural network training
EP3716156A4 (en)	2021-01-13	Neural network model training method and apparatus
EP3451241A4 (en)	2019-12-25	Device and method for performing training of convolutional neural network
EP3757905A4 (en)	2021-04-28	Deep neural network training method and apparatus
EP3407268A4 (en)	2019-08-28	Device and method for executing reversal training of artificial neural network
GB2581731B (en)	2022-11-09	Training of artificial neural networks
EP3503980A4 (en)	2020-04-29	Exercise system and method
EP3607493A4 (en)	2020-12-02	Methods and systems for budgeted and simplified training of deep neural networks
EP3633557A4 (en)	2020-09-16	Neural network calculation apparatus and method
EP3440659A4 (en)	2020-01-15	Cpr training system and method
EP3499800A4 (en)	2019-06-26	Microservice configuration apparatus and method
EP3607495A4 (en)	2020-11-25	Methods and systems using improved training and learning for deep neural networks
EP3425527A4 (en)	2019-11-27	Method of training machine learning system, and training system
EP3196809A4 (en)	2017-11-22	System and method for training parameter set in neural network
EP3627401A4 (en)	2020-07-29	Method and device for training neural network
EP3673419B8 (en)	2024-09-18	Population based training of neural networks
EP3451242A4 (en)	2019-12-25	Device and method for performing reversetraining of fully connected layers of neural network
EP3407265A4 (en)	2019-09-04	Device and method for executing forward calculation of artificial neural network
EP3282781A4 (en)	2018-05-16	Method and device for improving positioning performance of artificial neural network
EP3167941A4 (en)	2018-03-14	Muscle training method and muscle training system
EP3503429A4 (en)	2019-08-14	Beamforming training method and apparatus
EP3558475A4 (en)	2020-08-12	Seated treadmill and method of use
EP3598387A4 (en)	2020-01-22	Learning method and program
EP3552970A4 (en)	2020-12-16	Freefall training apparatus and training method using same

Legal Events

Date	Code	Title	Description
2017-12-16	STAA	Information on the status of an ep patent application or granted ep patent	Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE
2019-03-15	PUAI	Public reference made under article 153(3) epc to a published international application that has entered the european phase	Free format text: ORIGINAL CODE: 0009012
2019-03-15	STAA	Information on the status of an ep patent application or granted ep patent	Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE
2019-04-10	STAA	Information on the status of an ep patent application or granted ep patent	Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE
2019-04-17	17P	Request for examination filed	Effective date: 20181112
2019-04-17	AK	Designated contracting states	Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
2019-04-17	AX	Request for extension of the european patent	Extension state: BA ME
2019-09-18	DAV	Request for validation of the european patent (deleted)
2019-09-18	DAX	Request for extension of the european patent (deleted)
2020-02-26	A4	Supplementary search report drawn up and despatched	Effective date: 20200124
2020-02-26	RIC1	Information provided on ipc code assigned before grant	Ipc: G06N 3/02 20060101AFI20200120BHEP Ipc: G06F 17/16 20060101ALI20200120BHEP Ipc: G06N 3/04 20060101ALI20200120BHEP Ipc: G06N 3/063 20060101ALI20200120BHEP Ipc: G06F 15/00 20060101ALI20200120BHEP Ipc: G06N 3/08 20060101ALI20200120BHEP
2021-12-09	STAA	Information on the status of an ep patent application or granted ep patent	Free format text: STATUS: EXAMINATION IS IN PROGRESS
2021-12-10	STAA	Information on the status of an ep patent application or granted ep patent	Free format text: STATUS: EXAMINATION IS IN PROGRESS
2022-01-12	17Q	First examination report despatched	Effective date: 20211208
2022-10-14	STAA	Information on the status of an ep patent application or granted ep patent	Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN
2022-11-16	18D	Application deemed to be withdrawn	Effective date: 20220621