CN111492382B - 训练第一神经网络模型和第二神经网络模型 - Google Patents

训练第一神经网络模型和第二神经网络模型 Download PDF

Info

Publication number
CN111492382B
CN111492382B CN201880082613.0A CN201880082613A CN111492382B CN 111492382 B CN111492382 B CN 111492382B CN 201880082613 A CN201880082613 A CN 201880082613A CN 111492382 B CN111492382 B CN 111492382B
Authority
CN
China
Prior art keywords
model
neural network
network model
weights
processor
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
CN201880082613.0A
Other languages
English (en)
Chinese (zh)
Other versions
CN111492382A (zh
Inventor
B·G·格布雷
E·布雷施
D·马夫里厄杜斯
T·范登赫费尔
U·格罗塞卡特赫费尔
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.)
Koninklijke Philips NV
Original Assignee
Koninklijke Philips NV
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 Koninklijke Philips NV filed Critical Koninklijke Philips NV
Publication of CN111492382A publication Critical patent/CN111492382A/zh
Application granted granted Critical
Publication of CN111492382B publication Critical patent/CN111492382B/zh
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
    • 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
    • G06N3/0464—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
    • G06N3/04—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
    • G06N3/09—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
    • G06N3/08—Learning methods
    • G06N3/096—Transfer learning

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)
  • Image Analysis (AREA)
CN201880082613.0A 2017-11-20 2018-11-13 训练第一神经网络模型和第二神经网络模型 Active CN111492382B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201762588542P 2017-11-20 2017-11-20
US62/588,542 2017-11-20
PCT/EP2018/080991 WO2019096754A1 (en) 2017-11-20 2018-11-13 Training first and second neural network models

Publications (2)

Publication Number Publication Date
CN111492382A CN111492382A (zh) 2020-08-04
CN111492382B true CN111492382B (zh) 2024-05-07

Family

ID=64308755

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201880082613.0A Active CN111492382B (zh) 2017-11-20 2018-11-13 训练第一神经网络模型和第二神经网络模型

Country Status (4)

Country Link
US (1) US11657265B2 (https=)
JP (1) JP7325414B2 (https=)
CN (1) CN111492382B (https=)
WO (1) WO2019096754A1 (https=)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230195975A1 (en) * 2016-11-08 2023-06-22 Srinivas Bharadwaj Method and electronic device for performing imperfect emulation of state of model
US11995533B1 (en) 2018-12-05 2024-05-28 Perceive Corporation Executing replicated neural network layers on inference circuit
US11923088B2 (en) * 2019-08-30 2024-03-05 AR & NS Investment, LLC Artificial intelligence-based personalized health maintenance system to generate digital therapeutic environment for multi-modal therapy
US12072954B1 (en) * 2019-11-06 2024-08-27 Nvidia Corporation Neural network trained using federated learning with local training data preserved at local edge circuits
CN111105031B (zh) * 2019-11-11 2023-10-17 北京地平线机器人技术研发有限公司 网络结构搜索方法和装置、存储介质、电子设备
US11443235B2 (en) 2019-11-14 2022-09-13 International Business Machines Corporation Identifying optimal weights to improve prediction accuracy in machine learning techniques
CN111353580B (zh) * 2020-02-03 2023-06-20 中国人民解放军国防科技大学 目标检测网络的训练方法、电子设备及存储介质
CN111539947B (zh) * 2020-04-30 2024-03-29 上海商汤智能科技有限公司 图像检测方法及相关模型的训练方法和相关装置、设备
US20210357739A1 (en) * 2020-05-14 2021-11-18 Micron Technology, Inc. Memory device to train neural networks
CN113705591A (zh) * 2020-05-20 2021-11-26 上海微创卜算子医疗科技有限公司 可读存储介质、支架规格识别方法及装置
US12423570B2 (en) * 2020-06-10 2025-09-23 Nvidia Corporation Accelerated training for neural network models
CN111860840B (zh) * 2020-07-28 2023-10-17 上海联影医疗科技股份有限公司 深度学习模型训练方法、装置、计算机设备及存储介质
CN111950295A (zh) * 2020-08-10 2020-11-17 北京嘀嘀无限科技发展有限公司 一种训练自然语言处理模型的方法和系统
JP7613058B2 (ja) * 2020-11-17 2025-01-15 住友ゴム工業株式会社 タイヤの計測値の推定方法
US12367340B2 (en) * 2020-12-29 2025-07-22 International Business Machines Corporation Context aware personalization
US20220318666A1 (en) * 2021-03-30 2022-10-06 International Business Machines Corporation Training and scoring for large number of performance models
CN113240117B (zh) * 2021-06-01 2022-11-18 大连理工大学 一种变保真度迁移学习模型建立方法
US12455932B2 (en) * 2023-06-29 2025-10-28 Workday, Inc. Predictive feedback engine for improving search relevance in a tenant configurable hybrid search system

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0482375A2 (en) * 1990-10-22 1992-04-29 Motorola, Inc. Digital processing element in an artificial neural network
JP2008250856A (ja) * 2007-03-30 2008-10-16 Sony Corp 学習装置、学習方法、及びプログラム
CN104021390A (zh) * 2013-03-01 2014-09-03 佳能株式会社 模型生成装置、模式识别设备及其方法
CN105637540A (zh) * 2013-10-08 2016-06-01 谷歌公司 用于强化学习的方法和设备
CN106170800A (zh) * 2014-09-12 2016-11-30 微软技术许可有限责任公司 经由输出分布来学习学生dnn
US9542621B2 (en) * 2014-10-09 2017-01-10 Microsoft Technology Licensing, Llc Spatial pyramid pooling networks for image processing
CN106462806A (zh) * 2015-06-08 2017-02-22 首选网络株式会社 学习装置单元
CN106687995A (zh) * 2014-05-12 2017-05-17 高通股份有限公司 分布式模型学习
CN107256423A (zh) * 2017-05-05 2017-10-17 深圳市丰巨泰科电子有限公司 一种增广神经网架构及其训练方法、计算机可读存储介质

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5195169A (en) * 1989-03-03 1993-03-16 Sharp Kabushiki Kaisha Control device for controlling learning of a neural network
JPH03288258A (ja) * 1990-04-04 1991-12-18 Takayama:Kk データ処理装置の学習方法
JPH05197705A (ja) * 1991-07-09 1993-08-06 Fujitsu Ltd ニューラルネットワークの学習システム
US9119573B2 (en) 2009-12-10 2015-09-01 Siemens Aktiengesellschaft Stent marker detection using a learning based classifier in medical imaging
US20120002855A1 (en) 2010-06-30 2012-01-05 Fujifilm Corporation Stent localization in 3d cardiac images
WO2013012898A2 (en) * 2011-07-19 2013-01-24 Causata Inc. Distributed scalable incrementally updated models in decisioning systems
US20150301510A1 (en) * 2014-04-22 2015-10-22 Siegmund Düll Controlling a Target System
US20150324690A1 (en) * 2014-05-08 2015-11-12 Microsoft Corporation Deep Learning Training System
US20160140438A1 (en) * 2014-11-13 2016-05-19 Nec Laboratories America, Inc. Hyper-class Augmented and Regularized Deep Learning for Fine-grained Image Classification
US11423311B2 (en) * 2015-06-04 2022-08-23 Samsung Electronics Co., Ltd. Automatic tuning of artificial neural networks
US10878320B2 (en) 2015-07-22 2020-12-29 Qualcomm Incorporated Transfer learning in neural networks
US10679145B2 (en) * 2015-08-07 2020-06-09 Nec Corporation System and method for balancing computation with communication in parallel learning
KR102492318B1 (ko) * 2015-09-18 2023-01-26 삼성전자주식회사 모델 학습 방법 및 장치, 및 데이터 인식 방법
US20170132528A1 (en) 2015-11-06 2017-05-11 Microsoft Technology Licensing, Llc Joint model training
US10318848B2 (en) * 2015-12-15 2019-06-11 Qualcomm Incorporated Methods for object localization and image classification
KR102501838B1 (ko) * 2016-02-01 2023-02-23 삼성전자주식회사 심전도 신호를 이용한 인증 장치 및 방법
US10755199B2 (en) * 2017-05-30 2020-08-25 Adobe Inc. Introspection network for training neural networks
US11138724B2 (en) * 2017-06-01 2021-10-05 International Business Machines Corporation Neural network classification
JP6974712B2 (ja) * 2017-10-24 2021-12-01 富士通株式会社 探索方法、探索装置および探索プログラム
US10635978B2 (en) * 2017-10-26 2020-04-28 SparkCognition, Inc. Ensembling of neural network models

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0482375A2 (en) * 1990-10-22 1992-04-29 Motorola, Inc. Digital processing element in an artificial neural network
JP2008250856A (ja) * 2007-03-30 2008-10-16 Sony Corp 学習装置、学習方法、及びプログラム
CN104021390A (zh) * 2013-03-01 2014-09-03 佳能株式会社 模型生成装置、模式识别设备及其方法
CN105637540A (zh) * 2013-10-08 2016-06-01 谷歌公司 用于强化学习的方法和设备
CN106687995A (zh) * 2014-05-12 2017-05-17 高通股份有限公司 分布式模型学习
CN106170800A (zh) * 2014-09-12 2016-11-30 微软技术许可有限责任公司 经由输出分布来学习学生dnn
US9542621B2 (en) * 2014-10-09 2017-01-10 Microsoft Technology Licensing, Llc Spatial pyramid pooling networks for image processing
CN106462806A (zh) * 2015-06-08 2017-02-22 首选网络株式会社 学习装置单元
CN107256423A (zh) * 2017-05-05 2017-10-17 深圳市丰巨泰科电子有限公司 一种增广神经网架构及其训练方法、计算机可读存储介质

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
An Investigation of How Neural Networks Learn From the Experiences of Peers Through Periodic Weight Averaging;JOSHUA SMITH ET AL;IEEE;731-736 *
互学习神经网络训练方法研究;刘威等;《计算机学报》;第40卷(第6期);1291-1308 *

Also Published As

Publication number Publication date
US11657265B2 (en) 2023-05-23
WO2019096754A1 (en) 2019-05-23
US20190156205A1 (en) 2019-05-23
JP2021503661A (ja) 2021-02-12
JP7325414B2 (ja) 2023-08-14
CN111492382A (zh) 2020-08-04

Similar Documents

Publication Publication Date Title
CN111492382B (zh) 训练第一神经网络模型和第二神经网络模型
US11521064B2 (en) Training a neural network model
CN109241903B (zh) 样本数据清洗方法、装置、计算机设备及存储介质
US20220129791A1 (en) Systematic approach for explaining machine learning predictions
CN110349147B (zh) 模型的训练方法、眼底黄斑区病变识别方法、装置及设备
US20190354810A1 (en) Active learning to reduce noise in labels
US20180032841A1 (en) Medical Scanner Teaches Itself To Optimize Clinical Protocols And Image Acquisition
EP3474192A1 (en) Classifying data
JP7842253B2 (ja) 画像におけるオープンボキャブラリオブジェクト検出
US20220138573A1 (en) Methods and systems for training convolutional neural networks
JP2017224027A (ja) データのラベリングモデルに係る機械学習方法、コンピュータおよびプログラム
KR102246266B1 (ko) 레이블 정보에 대한 피드백을 제공하는 방법 및 시스템
CN109447096B (zh) 一种基于机器学习的扫视路径预测方法和装置
US12210946B2 (en) Machine learning based function testing
Galdran et al. A no-reference quality metric for retinal vessel tree segmentation
CN113656669A (zh) 标签更新方法及装置
US20220164659A1 (en) Deep Learning Error Minimizing System for Real-Time Generation of Big Data Analysis Models for Mobile App Users and Controlling Method for the Same
US20210319269A1 (en) Apparatus for determining a classifier for identifying objects in an image, an apparatus for identifying objects in an image and corresponding methods
CN114359587B (zh) 类激活图生成方法、可解释方法、装置、设备及存储介质
US12050991B1 (en) Connectomics-based neural architecture search
EP3624022A1 (en) Modifying a neural network
JP2022151502A (ja) プログラム、情報処理装置、及び方法
EP4657339A1 (en) Training resource allocation models
CN121564783B (zh) 一种基于因果特征门控的斜视检测方法
US20250363123A1 (en) Local context for context-based tabular classification

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant