JP7389575B2 - データ処理装置、データ処理方法、学習装置、学習方法、ニューラルネットワーク、及びプログラム - Google Patents

データ処理装置、データ処理方法、学習装置、学習方法、ニューラルネットワーク、及びプログラム Download PDF

Info

Publication number
JP7389575B2
JP7389575B2 JP2019123945A JP2019123945A JP7389575B2 JP 7389575 B2 JP7389575 B2 JP 7389575B2 JP 2019123945 A JP2019123945 A JP 2019123945A JP 2019123945 A JP2019123945 A JP 2019123945A JP 7389575 B2 JP7389575 B2 JP 7389575B2
Authority
JP
Japan
Prior art keywords
data
layer
learning
feature
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.)
Active
Application number
JP2019123945A
Other languages
English (en)
Japanese (ja)
Other versions
JP2021009622A (ja
JP2021009622A5 (enExample
Inventor
俊太 舘
ソクイ チン
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.)
Canon Inc
Original Assignee
Canon 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 Canon Inc filed Critical Canon Inc
Priority to JP2019123945A priority Critical patent/JP7389575B2/ja
Priority to US16/918,206 priority patent/US12079717B2/en
Publication of JP2021009622A publication Critical patent/JP2021009622A/ja
Publication of JP2021009622A5 publication Critical patent/JP2021009622A5/ja
Application granted granted Critical
Publication of JP7389575B2 publication Critical patent/JP7389575B2/ja
Priority to US18/787,158 priority patent/US20240386273A1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • 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
    • G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
    • 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
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • G06N3/0495—Quantised networks; Sparse networks; Compressed 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/067—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using optical means
    • 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • 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
    • 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
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn

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)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Physiology (AREA)
  • Image Analysis (AREA)
JP2019123945A 2019-07-02 2019-07-02 データ処理装置、データ処理方法、学習装置、学習方法、ニューラルネットワーク、及びプログラム Active JP7389575B2 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2019123945A JP7389575B2 (ja) 2019-07-02 2019-07-02 データ処理装置、データ処理方法、学習装置、学習方法、ニューラルネットワーク、及びプログラム
US16/918,206 US12079717B2 (en) 2019-07-02 2020-07-01 Data processing apparatus, training apparatus, method of detecting an object, method of training, and medium
US18/787,158 US20240386273A1 (en) 2019-07-02 2024-07-29 Data processing apparatus, training apparatus, method of detecting an object, method of training, and medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2019123945A JP7389575B2 (ja) 2019-07-02 2019-07-02 データ処理装置、データ処理方法、学習装置、学習方法、ニューラルネットワーク、及びプログラム

Publications (3)

Publication Number Publication Date
JP2021009622A JP2021009622A (ja) 2021-01-28
JP2021009622A5 JP2021009622A5 (enExample) 2022-07-11
JP7389575B2 true JP7389575B2 (ja) 2023-11-30

Family

ID=74065752

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2019123945A Active JP7389575B2 (ja) 2019-07-02 2019-07-02 データ処理装置、データ処理方法、学習装置、学習方法、ニューラルネットワーク、及びプログラム

Country Status (2)

Country Link
US (2) US12079717B2 (enExample)
JP (1) JP7389575B2 (enExample)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114077884B (zh) * 2020-08-20 2025-02-28 富泰华工业（深圳）有限公司 深度学习模型的模型转换优化装置、方法及可读存储介质
US12406023B1 (en) * 2021-01-04 2025-09-02 Nvidia Corporation Neural network training method
JP7621197B2 (ja) * 2021-06-08 2025-01-24 株式会社日立製作所 学習認識装置
US20230409673A1 (en) * 2022-06-20 2023-12-21 GE Precision Healthcare LLC Uncertainty scoring for neural networks via stochastic weight perturbations
JP2024041325A (ja) * 2022-09-14 2024-03-27 株式会社日立製作所 演算装置

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007305072A (ja) 2006-05-15 2007-11-22 Sony Corp 情報処理装置、情報処理方法、およびプログラム
JP2015210747A (ja) 2014-04-30 2015-11-24 国立研究開発法人情報通信研究機構 階層型ニューラルネットワークの学習システム及び方法

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9811775B2 (en) 2012-12-24 2017-11-07 Google Inc. Parallelizing neural networks during training

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007305072A (ja) 2006-05-15 2007-11-22 Sony Corp 情報処理装置、情報処理方法、およびプログラム
JP2015210747A (ja) 2014-04-30 2015-11-24 国立研究開発法人情報通信研究機構 階層型ニューラルネットワークの学習システム及び方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Pablo Barros, 外3名，"A multichannel convolutional neural network for hand posture recognition"，Proceedings of the 24th International Conference on Artificial Neural Networks(ICANN 2014)，2014年09月30日

Also Published As

Publication number Publication date
US20210004681A1 (en) 2021-01-07
US20240386273A1 (en) 2024-11-21
JP2021009622A (ja) 2021-01-28
US12079717B2 (en) 2024-09-03

Similar Documents

Publication Publication Date Title
JP7389575B2 (ja) データ処理装置、データ処理方法、学習装置、学習方法、ニューラルネットワーク、及びプログラム
Jin et al. Efficient multimodal large language models: A survey
CN113570029B (zh) 获取神经网络模型的方法、图像处理方法及装置
CN113435682B (zh) 分布式训练的梯度压缩
Zhang et al. STA-GCN: Two-stream graph convolutional network with spatial–temporal attention for hand gesture recognition
JP6714690B2 (ja) 情報処理システム、情報処理システムの運用方法、および機械学習演算器
WO2018058426A1 (zh) 硬件神经网络转换方法、计算装置、编译方法和神经网络软硬件协作系统
CN113449859A (zh) 一种数据处理方法及其装置
CN112561028B (zh) 训练神经网络模型的方法、数据处理的方法及装置
US20200151558A1 (en) Systems and methods for updating an artificial intelligence model by a subset of parameters in a communication system
CN115830179B (zh) 一种类别无关的遥感地物矢量拓扑结构提取方法
WO2021073104A1 (zh) 一种基于三维相变存储器的3d卷积运算装置及方法
CN113449612B (zh) 一种基于子流型稀疏卷积的三维目标点云识别的方法
JPWO2019135274A1 (ja) ニューラル・ネットワークを有するデータ処理システム
DE102019103319A1 (de) Stochastisches runden von zahlenwerten
US20220207327A1 (en) Method for dividing processing capabilities of artificial intelligence between devices and servers in network environment
WO2020003434A1 (ja) 機械学習方法、機械学習装置、及び機械学習プログラム
JP2020107042A (ja) 学習モデル生成装置、学習モデル生成方法、及びプログラム
Milutinovic et al. End-to-end training of differentiable pipelines across machine learning frameworks
CN111339874A (zh) 一种单级人脸分割的方法
CN118254168A (zh) 一种基于检测约束和深度强化学习的快速抓取方法
CN112784999A (zh) 基于注意力机制的mobilenet-v1知识蒸馏方法、存储器及终端设备
WO2022038660A1 (ja) 情報処理装置、情報処理方法、および、情報処理プログラム
CN119919768A (zh) 一种基于图信息传播的视觉令牌剪枝方法
Malpure et al. Investigating transfer learning capabilities of vision transformers and CNNs by fine-tuning a single trainable block

Legal Events

Date Code Title Description
RD01 Notification of change of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7421

Effective date: 20210103

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20210113

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20220701

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20220701

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20230731

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20230929

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20231020

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20231117

R151 Written notification of patent or utility model registration

Ref document number: 7389575

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R151