CN110799995A - 数据识别器训练方法、数据识别器训练装置、程序及训练方法 - Google Patents

数据识别器训练方法、数据识别器训练装置、程序及训练方法 Download PDF

Info

Publication number
CN110799995A
CN110799995A CN201880043309.5A CN201880043309A CN110799995A CN 110799995 A CN110799995 A CN 110799995A CN 201880043309 A CN201880043309 A CN 201880043309A CN 110799995 A CN110799995 A CN 110799995A
Authority
CN
China
Prior art keywords
data
aforementioned
weight matrix
recognizer
error
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
CN201880043309.5A
Other languages
English (en)
Chinese (zh)
Inventor
宫户岳
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.)
Preferred Networks Inc
Original Assignee
Preferred Networks 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 Preferred Networks Inc filed Critical Preferred Networks Inc
Publication of CN110799995A publication Critical patent/CN110799995A/zh
Pending legal-status Critical Current

Links

Images

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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N3/088—Non-supervised learning, e.g. competitive 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
    • G06N3/0464—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
    • G06N3/047—Probabilistic or stochastic 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
    • G06N3/0475—Generative 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
    • G06N3/08—Learning methods
    • G06N3/091—Active 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
    • G06N3/094—Adversarial 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
    • G06N3/048—Activation functions

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)
CN201880043309.5A 2017-06-29 2018-06-28 数据识别器训练方法、数据识别器训练装置、程序及训练方法 Pending CN110799995A (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
JP2017127769 2017-06-29
JP2017-127769 2017-06-29
PCT/JP2018/024569 WO2019004350A1 (ja) 2017-06-29 2018-06-28 データ識別器訓練方法、データ識別器訓練装置、プログラム及び訓練方法

Publications (1)

Publication Number Publication Date
CN110799995A true CN110799995A (zh) 2020-02-14

Family

ID=64742063

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201880043309.5A Pending CN110799995A (zh) 2017-06-29 2018-06-28 数据识别器训练方法、数据识别器训练装置、程序及训练方法

Country Status (5)

Country Link
US (2) US11593663B2 (https=)
EP (1) EP3648017A4 (https=)
JP (4) JP6595151B2 (https=)
CN (1) CN110799995A (https=)
WO (1) WO2019004350A1 (https=)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111461340A (zh) * 2020-03-10 2020-07-28 北京百度网讯科技有限公司 权重矩阵的更新方法、装置及电子设备
CN111553587A (zh) * 2020-04-26 2020-08-18 中国电力科学研究院有限公司 一种基于对抗学习模型的新能源场景生成方法及系统
CN113438190A (zh) * 2021-06-22 2021-09-24 电子科技大学 神经网络训练方法及装置、mimo均衡器与方法、可读介质
CN113806338A (zh) * 2021-11-18 2021-12-17 深圳索信达数据技术有限公司 一种基于数据样本图像化的数据甄别的方法与系统
CN116011609A (zh) * 2022-10-28 2023-04-25 支付宝(杭州)信息技术有限公司 训练时序预测模型、预测行为序列的方法和装置
CN116109853A (zh) * 2021-11-09 2023-05-12 广州视源电子科技股份有限公司 任务处理模型训练、任务处理方法、装置及设备
CN116302294A (zh) * 2023-05-18 2023-06-23 安元科技股份有限公司 一种界面化自动识别组件属性的方法及系统
CN118410341A (zh) * 2024-05-14 2024-07-30 北京世纪好未来教育科技有限公司 错误检测模型的训练方法、错误检测方法、装置及设备

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019004350A1 (ja) 2017-06-29 2019-01-03 株式会社 Ｐｒｅｆｅｒｒｅｄ Ｎｅｔｗｏｒｋｓ データ識別器訓練方法、データ識別器訓練装置、プログラム及び訓練方法
JP7023669B2 (ja) 2017-10-26 2022-02-22 株式会社Preferred Networks 画像生成方法、画像生成装置、及び画像生成プログラム
EP3735655A1 (en) * 2018-01-02 2020-11-11 Nokia Technologies Oy Channel modelling in a data transmission system
US11797864B2 (en) * 2018-06-18 2023-10-24 Fotonation Limited Systems and methods for conditional generative models
US20200143266A1 (en) * 2018-11-07 2020-05-07 International Business Machines Corporation Adversarial balancing for causal inference
JP7198432B2 (ja) * 2019-01-30 2023-01-04 京セラドキュメントソリューションズ株式会社 画像処理装置、画像読取装置、画像形成装置、画像処理方法及び画像処理プログラム
JP7370158B2 (ja) * 2019-04-03 2023-10-27 株式会社Preferred Networks 情報処理装置および情報処理方法
JP2020196102A (ja) * 2019-06-04 2020-12-10 株式会社Ｐｒｅｆｅｒｒｅｄ Ｎｅｔｗｏｒｋｓ 制御装置、システム、学習装置および制御方法
CN110365647B (zh) * 2019-06-13 2021-09-14 广东工业大学 一种基于pca和bp神经网络的虚假数据注入攻击检测方法
EP3963872B1 (en) 2019-08-30 2024-01-17 Samsung Electronics Co., Ltd. Electronic apparatus for applying personalized artificial intelligence model to another model
KR102788804B1 (ko) * 2019-12-27 2025-03-31 삼성전자주식회사 전자 장치 및 그 제어 방법
CN111639861B (zh) * 2020-06-01 2023-06-23 上海大学 一种基于神经网络的绩效考核方法及系统
TWI768555B (zh) * 2020-11-23 2022-06-21 威盛電子股份有限公司 調整神經網路輸入資料的系統及方法
CN115374899A (zh) * 2021-05-19 2022-11-22 富泰华工业（深圳）有限公司 生成对抗网络优化方法及电子设备
CN117296050B (zh) * 2021-05-25 2025-01-14 维萨国际服务协会 用于使交叉嵌入对齐的嵌入归一化的方法、系统和计算机程序产品
JP7487144B2 (ja) * 2021-06-09 2024-05-20 株式会社東芝 情報処理装置、方法及びプログラム
US20240119295A1 (en) * 2021-11-02 2024-04-11 Google Llc Generalized Bags for Learning from Label Proportions
CN114463599B (zh) * 2022-02-13 2025-03-25 北京师范大学 对抗生成网络快速训练方法、装置、设备和存储介质
CN116090517B (zh) * 2022-12-30 2026-02-24 杭州华橙软件技术有限公司 模型训练方法、目标检测方法、装置以及可读存储介质
CN118129088B (zh) * 2024-03-13 2024-09-06 新疆维吾尔自治区特种设备检验研究院 一种基于人工智能的压力管道电磁超声检测方法

Family Cites Families (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1993010500A1 (en) * 1991-11-13 1993-05-27 Iowa State University Research Foundation, Inc. Improved memory capacity neural network
US5479523A (en) * 1994-03-16 1995-12-26 Eastman Kodak Company Constructing classification weights matrices for pattern recognition systems using reduced element feature subsets
US6987819B2 (en) * 2000-12-29 2006-01-17 Motorola, Inc. Method and device for multiple input/multiple output transmit and receive weights for equal-rate data streams
JP4604545B2 (ja) * 2004-05-10 2011-01-05 ソニー株式会社 無線通信システム、無線通信装置及び無線通信方法ム
JP5248130B2 (ja) * 2008-01-31 2013-07-31 株式会社東芝 無線送信方法及び装置
JP5221285B2 (ja) * 2008-11-05 2013-06-26 株式会社東芝 無線通信装置及び方法
JPWO2010150313A1 (ja) * 2009-06-25 2012-12-06 株式会社東芝 通信装置
US9189703B2 (en) * 2012-07-09 2015-11-17 Canon Kabushiki Kaisha Systems and methods for colorimetric and spectral material estimation
US9400955B2 (en) * 2013-12-13 2016-07-26 Amazon Technologies, Inc. Reducing dynamic range of low-rank decomposition matrices
US10515304B2 (en) * 2015-04-28 2019-12-24 Qualcomm Incorporated Filter specificity as training criterion for neural networks
JP6450053B2 (ja) * 2015-08-15 2019-01-09 セールスフォース ドット コム インコーポレイティッド ３ｄバッチ正規化を伴う三次元（３ｄ）畳み込み
US10521718B1 (en) * 2015-09-28 2019-12-31 Google Llc Adversarial training of neural networks
CN116468070A (zh) * 2015-11-12 2023-07-21 渊慧科技有限公司 使用规范化的目标输出训练神经网络
JP6740247B2 (ja) 2015-12-01 2020-08-12 株式会社Ｐｒｅｆｅｒｒｅｄ Ｎｅｔｗｏｒｋｓ 異常検出システム、異常検出方法、異常検出プログラム及び学習済モデル生成方法
US10776712B2 (en) 2015-12-02 2020-09-15 Preferred Networks, Inc. Generative machine learning systems for drug design
US20190303743A1 (en) * 2016-08-13 2019-10-03 Intel Corporation Apparatuses, methods, and systems for neural networks
CN107785016A (zh) * 2016-08-31 2018-03-09 株式会社东芝 训练神经网络辅助模型的方法和装置及语音识别方法和装置
US11164076B2 (en) * 2016-10-20 2021-11-02 Uber Technologies, Inc. Intelligent regularization of neural network architectures
US10685285B2 (en) * 2016-11-23 2020-06-16 Microsoft Technology Licensing, Llc Mirror deep neural networks that regularize to linear networks
WO2018184102A1 (en) * 2017-04-03 2018-10-11 Royal Bank Of Canada Systems and methods for malicious code detection
WO2019004350A1 (ja) * 2017-06-29 2019-01-03 株式会社 Ｐｒｅｆｅｒｒｅｄ Ｎｅｔｗｏｒｋｓ データ識別器訓練方法、データ識別器訓練装置、プログラム及び訓練方法
US20200272906A1 (en) * 2017-11-07 2020-08-27 Nec Corporation Discriminant model generation device, discriminant model generation method, and discriminant model generation program
US10803347B2 (en) * 2017-12-01 2020-10-13 The University Of Chicago Image transformation with a hybrid autoencoder and generative adversarial network machine learning architecture
US10846593B2 (en) * 2018-04-27 2020-11-24 Qualcomm Technologies Inc. System and method for siamese instance search tracker with a recurrent neural network
US11170256B2 (en) * 2018-09-26 2021-11-09 Nec Corporation Multi-scale text filter conditioned generative adversarial networks
US10997464B2 (en) * 2018-11-09 2021-05-04 Adobe Inc. Digital image layout training using wireframe rendering within a generative adversarial network (GAN) system
EP3937094A4 (en) * 2019-03-04 2022-04-27 Panasonic Intellectual Property Corporation of America Information processing method and information processing system
US12167100B2 (en) * 2019-03-21 2024-12-10 Samsung Electronics Co., Ltd. Method, apparatus, device and medium for generating captioning information of multimedia data
US11164085B2 (en) * 2019-04-25 2021-11-02 Booz Allen Hamilton Inc. System and method for training a neural network system
EP3973459B1 (en) * 2019-05-23 2025-07-02 DeepMind Technologies Limited Generative adversarial networks with temporal and spatial discriminators for efficient video generation
EP3963872B1 (en) * 2019-08-30 2024-01-17 Samsung Electronics Co., Ltd. Electronic apparatus for applying personalized artificial intelligence model to another model
JP7021158B2 (ja) * 2019-09-04 2022-02-16 株式会社東芝 ロボットシステムおよび駆動方法
JP7051772B2 (ja) * 2019-09-12 2022-04-11 株式会社東芝 提供装置、提供方法及びプログラム
CN110827216B (zh) * 2019-10-23 2023-07-14 上海理工大学 图像去噪的多生成器生成对抗网络学习方法
EP3971773B1 (en) * 2020-03-11 2026-03-11 Shenzhen Institutes of Advanced Technology Visualization method and device for evaluating brain addiction traits, and medium
US11436498B2 (en) * 2020-06-09 2022-09-06 Toyota Research Institute, Inc. Neural architecture search system for generating a neural network architecture
DE102021201833A1 (de) * 2021-02-26 2022-09-01 Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung eingetragener Verein Vorrichtung zur Verarbeitung von mindestens einem Eingangsdatensatz unter Verwendung eines neuronalen Netzes sowie Verfahren
CN115049917B (zh) * 2022-08-17 2022-11-15 上海与光彩芯科技有限公司 神经网络的训练方法、物体检测方法和智能终端设备

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111461340A (zh) * 2020-03-10 2020-07-28 北京百度网讯科技有限公司 权重矩阵的更新方法、装置及电子设备
CN111461340B (zh) * 2020-03-10 2023-03-31 北京百度网讯科技有限公司 权重矩阵的更新方法、装置及电子设备
CN111553587A (zh) * 2020-04-26 2020-08-18 中国电力科学研究院有限公司 一种基于对抗学习模型的新能源场景生成方法及系统
CN111553587B (zh) * 2020-04-26 2023-04-18 中国电力科学研究院有限公司 一种基于对抗学习模型的新能源场景生成方法及系统
CN113438190A (zh) * 2021-06-22 2021-09-24 电子科技大学 神经网络训练方法及装置、mimo均衡器与方法、可读介质
CN116109853A (zh) * 2021-11-09 2023-05-12 广州视源电子科技股份有限公司 任务处理模型训练、任务处理方法、装置及设备
CN113806338A (zh) * 2021-11-18 2021-12-17 深圳索信达数据技术有限公司 一种基于数据样本图像化的数据甄别的方法与系统
CN113806338B (zh) * 2021-11-18 2022-02-18 深圳索信达数据技术有限公司 一种基于数据样本图像化的数据甄别的方法与系统
CN116011609A (zh) * 2022-10-28 2023-04-25 支付宝(杭州)信息技术有限公司 训练时序预测模型、预测行为序列的方法和装置
CN116302294A (zh) * 2023-05-18 2023-06-23 安元科技股份有限公司 一种界面化自动识别组件属性的方法及系统
CN116302294B (zh) * 2023-05-18 2023-09-01 安元科技股份有限公司 一种界面化自动识别组件属性的方法及系统
CN118410341A (zh) * 2024-05-14 2024-07-30 北京世纪好未来教育科技有限公司 错误检测模型的训练方法、错误检测方法、装置及设备

Also Published As

Publication number Publication date
JPWO2019004350A1 (ja) 2019-11-07
JP6595151B2 (ja) 2019-10-23
JP7315748B2 (ja) 2023-07-26
WO2019004350A1 (ja) 2019-01-03
JP2022101650A (ja) 2022-07-06
JP6625785B1 (ja) 2019-12-25
US20200134473A1 (en) 2020-04-30
JP7064479B2 (ja) 2022-05-10
JP2020021496A (ja) 2020-02-06
EP3648017A1 (en) 2020-05-06
JP2020038704A (ja) 2020-03-12
US11593663B2 (en) 2023-02-28
US20230162045A1 (en) 2023-05-25
US11842284B2 (en) 2023-12-12
EP3648017A4 (en) 2021-08-04

Similar Documents

Publication Publication Date Title
CN110799995A (zh) 数据识别器训练方法、数据识别器训练装置、程序及训练方法
US12217187B2 (en) Methods and systems for cross-domain few-shot classification
US11151450B2 (en) System and method for generating explainable latent features of machine learning models
CN106096535B (zh) 一种基于双线性联合cnn的人脸验证方法
WO2022006919A1 (zh) 基于激活定点拟合的卷积神经网络训练后量化方法及系统
CN107578028B (zh) 一种人脸识别方法、装置、设备及计算机可读存储介质
CN106295694B (zh) 一种迭代重约束组稀疏表示分类的人脸识别方法
JP2020524861A (ja) セマンティックセグメンテーションモデルの訓練方法および装置、電子機器、ならびに記憶媒体
US11526760B2 (en) Training system for artificial neural networks having a global weight constrainer
US20140204092A1 (en) Classification of high dimensional data
CN111079790B (zh) 一种构建类别中心的图像分类方法
US20250378131A1 (en) Resilience determination and damage recovery in neural networks
WO2021042857A1 (zh) 图像分割模型的处理方法和处理装置
WO2022105108A1 (zh) 一种网络数据分类方法、装置、设备及可读存储介质
CN112836629A (zh) 一种图像分类方法
US11875263B2 (en) Method and apparatus for energy-aware deep neural network compression
CN112101513A (zh) 机器学习装置
CN110717402A (zh) 一种基于层级优化度量学习的行人再识别方法
US20230185998A1 (en) System and method for ai-assisted system design
CN110188621A (zh) 一种基于ssf-il-cnn的三维人脸表情识别方法
CN111310516B (zh) 一种行为识别方法和装置
CN120218187A (zh) 一种基于可训练类原型的个性化联邦学习方法
CN112348118A (zh) 基于梯度维持的图像分类方法、存储介质及电子设备
KR102539876B1 (ko) 인공지능 기술을 이용한 적층형 저항 변화 메모리 소자의 계층 최적화 시스템 및 그 방법
CN113139505B (zh) 半监督学习的方法及系统

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