[go: up one dir, main page]

GB2588614B - Method and system for customising a machine learning model - Google Patents

Method and system for customising a machine learning model Download PDF

Info

Publication number
GB2588614B
GB2588614B GB1915637.1A GB201915637A GB2588614B GB 2588614 B GB2588614 B GB 2588614B GB 201915637 A GB201915637 A GB 201915637A GB 2588614 B GB2588614 B GB 2588614B
Authority
GB
United Kingdom
Prior art keywords
customising
machine learning
learning model
model
machine
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.)
Active
Application number
GB1915637.1A
Other versions
GB201915637D0 (en
GB2588614A (en
Inventor
Zhu Xiatian
Perez-Rua Juan
Xiang Tao
Hospedales Timothy
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.)
Samsung Electronics Co Ltd
Original Assignee
Samsung Electronics Co 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 Samsung Electronics Co Ltd filed Critical Samsung Electronics Co Ltd
Priority to GB1915637.1A priority Critical patent/GB2588614B/en
Publication of GB201915637D0 publication Critical patent/GB201915637D0/en
Priority to KR1020200036344A priority patent/KR20210052153A/en
Priority to EP20883551.2A priority patent/EP3997625A4/en
Priority to PCT/KR2020/007560 priority patent/WO2021085785A1/en
Priority to US16/901,685 priority patent/US11797824B2/en
Publication of GB2588614A publication Critical patent/GB2588614A/en
Application granted granted Critical
Publication of GB2588614B publication Critical patent/GB2588614B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Medical Informatics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
GB1915637.1A 2019-10-29 2019-10-29 Method and system for customising a machine learning model Active GB2588614B (en)

Priority Applications (5)

Application Number Priority Date Filing Date Title
GB1915637.1A GB2588614B (en) 2019-10-29 2019-10-29 Method and system for customising a machine learning model
KR1020200036344A KR20210052153A (en) 2019-10-29 2020-03-25 Electronic apparatus and method for controlling thereof
EP20883551.2A EP3997625A4 (en) 2019-10-29 2020-06-11 ELECTRONIC DEVICE AND ASSOCIATED CONTROL METHOD
PCT/KR2020/007560 WO2021085785A1 (en) 2019-10-29 2020-06-11 Electronic apparatus and method for controlling thereof
US16/901,685 US11797824B2 (en) 2019-10-29 2020-06-15 Electronic apparatus and method for controlling thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
GB1915637.1A GB2588614B (en) 2019-10-29 2019-10-29 Method and system for customising a machine learning model

Publications (3)

Publication Number Publication Date
GB201915637D0 GB201915637D0 (en) 2019-12-11
GB2588614A GB2588614A (en) 2021-05-05
GB2588614B true GB2588614B (en) 2023-01-11

Family

ID=68768880

Family Applications (1)

Application Number Title Priority Date Filing Date
GB1915637.1A Active GB2588614B (en) 2019-10-29 2019-10-29 Method and system for customising a machine learning model

Country Status (2)

Country Link
KR (1) KR20210052153A (en)
GB (1) GB2588614B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114625876B (en) * 2022-03-17 2024-04-16 北京字节跳动网络技术有限公司 Method for generating author characteristic model, method and device for processing author information
EP4429202A1 (en) * 2023-03-09 2024-09-11 Abb Schweiz Ag Method for providing an efficient communication in a hierarchical network of distributed devices

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100177956A1 (en) * 2009-01-13 2010-07-15 Matthew Cooper Systems and methods for scalable media categorization
EP2689650A1 (en) * 2012-07-27 2014-01-29 Honda Research Institute Europe GmbH Trainable autonomous lawn mower
US20150254532A1 (en) * 2014-03-07 2015-09-10 Qualcomm Incorporated Photo management
US20150324688A1 (en) * 2014-05-12 2015-11-12 Qualcomm Incorporated Customized classifier over common features
WO2016149147A1 (en) * 2015-03-17 2016-09-22 Qualcomm Incorporated Sample selection for retraining classifiers
US20180039887A1 (en) * 2016-08-08 2018-02-08 EyeEm Mobile GmbH Systems, methods, and computer program products for extending, augmenting and enhancing searching and sorting capabilities by learning and adding concepts on the fly
US20180330238A1 (en) * 2017-05-09 2018-11-15 Neurala, Inc. Systems and methods to enable continual, memory-bounded learning in artificial intelligence and deep learning continuously operating applications across networked compute edges

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100177956A1 (en) * 2009-01-13 2010-07-15 Matthew Cooper Systems and methods for scalable media categorization
EP2689650A1 (en) * 2012-07-27 2014-01-29 Honda Research Institute Europe GmbH Trainable autonomous lawn mower
US20150254532A1 (en) * 2014-03-07 2015-09-10 Qualcomm Incorporated Photo management
US20150324688A1 (en) * 2014-05-12 2015-11-12 Qualcomm Incorporated Customized classifier over common features
WO2016149147A1 (en) * 2015-03-17 2016-09-22 Qualcomm Incorporated Sample selection for retraining classifiers
US20180039887A1 (en) * 2016-08-08 2018-02-08 EyeEm Mobile GmbH Systems, methods, and computer program products for extending, augmenting and enhancing searching and sorting capabilities by learning and adding concepts on the fly
US20180330238A1 (en) * 2017-05-09 2018-11-15 Neurala, Inc. Systems and methods to enable continual, memory-bounded learning in artificial intelligence and deep learning continuously operating applications across networked compute edges

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Arxiv.org, Gidaris et al, "Dynamic Few-Shot Visual Learning without Forgetting", 2018, available from https://arxiv.org/pdf/1804.09458.pdf *
Arxiv.org, Qi et al, "Low-Shot Learning with Imprinted Weights", 2018, available from https://arxiv.org/pdf/1712.07136.pdf *

Also Published As

Publication number Publication date
GB201915637D0 (en) 2019-12-11
KR20210052153A (en) 2021-05-10
GB2588614A (en) 2021-05-05

Similar Documents

Publication Publication Date Title
SG11202012505SA (en) System and method for training a damage identification model
ZA202106137B (en) System and method for inspecting a rail using machine learning
GB2604492B (en) Machine learning model for task and motion planning
EP3989131A4 (en) Method and system for realizing machine learning modeling process
GB2587820B (en) System and method for automatically detecting a security vulnerability in a source code using a machine learning model
EP3985578A4 (en) METHOD AND SYSTEM FOR AUTOMATIC TRAINING A MACHINE LEARNING MODEL
GB201710877D0 (en) A method and an apparatus for evaluating generative machine learning model
SG11202103308SA (en) Machine comprising a hybrid powertrain and corresponding control method
EP3648044A4 (en) METHOD, DEVICE AND DEVICE FOR TRAINING A RISK CONTROL MODEL AND RISK CONTROL
EP3759656A4 (en) System and method for a thing machine to perform models
GB202006063D0 (en) Methods and systems for training a machine learning model
SG11202105436YA (en) Method and system for generating training data for a machine learning model for predicting performance in electronic design
GB2577899B (en) A machine, controller, and control method
GB202116740D0 (en) Job value model generation method and system
GB201904438D0 (en) A method and system for access control
GB2588614B (en) Method and system for customising a machine learning model
GB201908494D0 (en) Computer-implemented methods for training a machine learning algorithm
GB201821322D0 (en) A computer program product and method for teaching computer programming
GB202005946D0 (en) A system and method for localisation
GB202315612D0 (en) Systems and methods for optimizing a machine learning model
GB2573509B (en) Method and system for providing display redundancy on a machine
GB202103918D0 (en) Machine learning model management
IL291678A (en) Method for producing a pipeline arrangement and pipeline arrangement
GB202018211D0 (en) Machine learning system and machine learning method
HUE065179T2 (en) Method for communicating in a network-distributed process control system and network-distributed process control system