[go: up one dir, main page]

EP3977364A4 - Method and processing device for training a neural network - Google Patents

Method and processing device for training a neural network Download PDF

Info

Publication number
EP3977364A4
EP3977364A4 EP20813093.0A EP20813093A EP3977364A4 EP 3977364 A4 EP3977364 A4 EP 3977364A4 EP 20813093 A EP20813093 A EP 20813093A EP 3977364 A4 EP3977364 A4 EP 3977364A4
Authority
EP
European Patent Office
Prior art keywords
training
processing device
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.)
Pending
Application number
EP20813093.0A
Other languages
German (de)
French (fr)
Other versions
EP3977364A1 (en
Inventor
Maryam ZIAEEFARD
Simon CORBEIL-LETOURNEAU
David Beach
Freddy Lecue
Florian MARTET
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.)
Thales Canada Inc
Original Assignee
Thales Canada 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.)
Filing date
Publication date
Application filed by Thales Canada Inc filed Critical Thales Canada Inc
Publication of EP3977364A1 publication Critical patent/EP3977364A1/en
Publication of EP3977364A4 publication Critical patent/EP3977364A4/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Algebra (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Image Analysis (AREA)
EP20813093.0A 2019-05-31 2020-05-28 Method and processing device for training a neural network Pending EP3977364A4 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201962855340P 2019-05-31 2019-05-31
PCT/IB2020/055088 WO2020240477A1 (en) 2019-05-31 2020-05-28 Method and processing device for training a neural network

Publications (2)

Publication Number Publication Date
EP3977364A1 EP3977364A1 (en) 2022-04-06
EP3977364A4 true EP3977364A4 (en) 2023-06-14

Family

ID=73553098

Family Applications (1)

Application Number Title Priority Date Filing Date
EP20813093.0A Pending EP3977364A4 (en) 2019-05-31 2020-05-28 Method and processing device for training a neural network

Country Status (3)

Country Link
EP (1) EP3977364A4 (en)
CA (2) CA3137030A1 (en)
WO (1) WO2020240477A1 (en)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112528810A (en) * 2020-12-04 2021-03-19 北京中科慧眼科技有限公司 Semantic segmentation method, system and equipment suitable for mobile terminal deployment
CN112686817B (en) * 2020-12-25 2023-04-07 天津中科智能识别产业技术研究院有限公司 Image completion method based on uncertainty estimation
CN112784818B (en) * 2021-03-03 2023-03-14 电子科技大学 Identification method based on grouping type active learning on optical remote sensing image
EP4341913A2 (en) * 2021-05-17 2024-03-27 Deep Safety GmbH System for detection and management of uncertainty in perception systems, for new object detection and for situation anticipation
US20240288764A1 (en) * 2021-07-06 2024-08-29 Asml Netherlands B.V. Determining localized image prediction errors to improve a machine learning model in predicting an image
CN113569926A (en) * 2021-07-13 2021-10-29 中国资源卫星应用中心 A method and device for training a cloud segmentation model with high mobility
WO2023000159A1 (en) * 2021-07-20 2023-01-26 海南长光卫星信息技术有限公司 Semi-supervised classification method, apparatus and device for high-resolution remote sensing image, and medium
CN113435411B (en) * 2021-07-26 2022-06-17 中国矿业大学(北京) Improved DeepLabV3+ based open pit land utilization identification method
CN113850825B (en) * 2021-09-27 2024-03-29 太原理工大学 Remote sensing image road segmentation method based on context information and multi-scale feature fusion
CN114494959B (en) * 2022-01-24 2025-03-25 中国矿业大学 An Attention-Guided Adversarial Attack Method for Video Object Segmentation
CN114595748B (en) * 2022-02-21 2024-02-13 南昌大学 A data segmentation method for fall protection systems
CN115546225B (en) * 2022-09-06 2025-07-08 华南理工大学 Model training method for improving semantic segmentation network prediction probability distribution quality
CN116434037B (en) * 2023-04-21 2023-09-22 大连理工大学 Multi-mode remote sensing target robust recognition method based on double-layer optimization learning
CN117036941B (en) * 2023-08-07 2025-09-19 电子科技大学长三角研究院(湖州) Building change detection method and system based on twin Unet model
CN117598713B (en) * 2023-11-30 2024-12-24 网易传媒科技（北京）有限公司 Abnormal discharge detection method, device, medium and equipment for epileptic seizure interval
CN119579460B (en) * 2024-11-19 2025-11-18 东南大学 A method and system for generalized sharpening of remote sensing images based on two-stage optimization-driven high-frequency enhancement
CN120430418B (en) * 2025-07-01 2025-09-30 科大讯飞股份有限公司 Large model reasoning method, device, related equipment and computer program product

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180182101A1 (en) * 2016-12-23 2018-06-28 Heartflow, Inc. Systems and methods for probabilistic segmentation in anatomical image processing

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10192129B2 (en) * 2015-11-18 2019-01-29 Adobe Systems Incorporated Utilizing interactive deep learning to select objects in digital visual media
GB201709672D0 (en) * 2017-06-16 2017-08-02 Ucl Business Plc A system and computer-implemented method for segmenting an image
CN109035263B (en) * 2018-08-14 2021-10-15 电子科技大学 An automatic segmentation method of brain tumor images based on convolutional neural network

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180182101A1 (en) * 2016-12-23 2018-06-28 Heartflow, Inc. Systems and methods for probabilistic segmentation in anatomical image processing

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
See also references of WO2020240477A1 *
WU DI ET AL: "Deep Dynamic Neural Networks for Multimodal Gesture Segmentation and Recognition", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, IEEE COMPUTER SOCIETY, USA, vol. 38, no. 8, 1 August 2016 (2016-08-01), pages 1583 - 1597, XP011615571, ISSN: 0162-8828, [retrieved on 20160630], DOI: 10.1109/TPAMI.2016.2537340 *

Also Published As

Publication number Publication date
CA3137030A1 (en) 2020-12-03
CA3242569A1 (en) 2020-12-03
WO2020240477A1 (en) 2020-12-03
EP3977364A1 (en) 2022-04-06

Similar Documents

Publication Publication Date Title
EP3977364A4 (en) Method and processing device for training a neural network
EP4064130A4 (en) Neural network model update method, and image processing method and device
EP4167130A4 (en) Neural network training method and related device
SG11202106979WA (en) Neural network training method and apparatus, and image processing method and apparatus
EP3857447A4 (en) Apparatus and method for image processing, and system for training neural network
EP3757905A4 (en) Deep neural network training method and apparatus
EP3964998A4 (en) Text processing method and model training method and apparatus
EP4024232A4 (en) Text processing model training method, and text processing method and apparatus
EP3968179A4 (en) Place recognition method and apparatus, model training method and apparatus for place recognition, and electronic device
EP3912106A4 (en) Apparatus and a method for neural network compression
EP4024261A4 (en) Model training method, apparatus, and system
EP4262121A4 (en) Neural network training method and related apparatus
EP3726476A4 (en) Object modeling movement method, apparatus and device
SG11202106062WA (en) Neural network training method and image matching method and device
SG11202103656SA (en) Task processing method based on neural network, and related device
SG11202101353TA (en) A method and apparatus for training a neural network to identify cracks
EP3933693A4 (en) Object recognition method and device
EP3777195A4 (en) An apparatus, a method and a computer program for running a neural network
EP4170548A4 (en) Method and device for constructing neural network
GB201900469D0 (en) Method and system for training a chatbot
EP3776451A4 (en) Image processing apparatus, image processing method thereof, image processing system, and training method thereof
EP3848855A4 (en) Learning method and apparatus for intention recognition model, and device
SG11202100364SA (en) Neural network training method and apparatus, gaze tracking method and apparatus, and electronic device
SG11202105631YA (en) Image processing method and device, and network training method and device
EP4414862A4 (en) Point cloud data processing method, neural network training method, and related device

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

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

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20211108

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

REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 40065389

Country of ref document: HK

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
A4 Supplementary search report drawn up and despatched

Effective date: 20230512

RIC1 Information provided on ipc code assigned before grant

Ipc: G06N 7/01 20230101ALI20230508BHEP

Ipc: G06N 3/09 20230101ALI20230508BHEP

Ipc: G06N 3/08 20060101AFI20230508BHEP

RAP3 Party data changed (applicant data changed or rights of an application transferred)

Owner name: THALES CANADA INC.