JP7353198B2 - 計算機、識別器の学習方法、および分析システム - Google Patents
計算機、識別器の学習方法、および分析システム Download PDFInfo
- Publication number
- JP7353198B2 JP7353198B2 JP2020018575A JP2020018575A JP7353198B2 JP 7353198 B2 JP7353198 B2 JP 7353198B2 JP 2020018575 A JP2020018575 A JP 2020018575A JP 2020018575 A JP2020018575 A JP 2020018575A JP 7353198 B2 JP7353198 B2 JP 7353198B2
- Authority
- JP
- Japan
- Prior art keywords
- data
- learning
- classifier
- evaluation
- discriminator
- 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
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
- G06N20/00—Machine 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
- G06N3/0464—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
- G06N3/0475—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
- G06N3/082—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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2020018575A JP7353198B2 (ja) | 2020-02-06 | 2020-02-06 | 計算機、識別器の学習方法、および分析システム |
| US17/795,291 US12536435B2 (en) | 2020-02-06 | 2021-01-18 | Computing machine, learning method of classifier, and analysis system |
| PCT/JP2021/001513 WO2021157330A1 (ja) | 2020-02-06 | 2021-01-18 | 計算機、識別器の学習方法、および分析システム |
| CN202180008949.4A CN114945940B (zh) | 2020-02-06 | 2021-01-18 | 计算机、识别器的学习方法以及分析系统 |
| EP21751391.0A EP4102454A4 (en) | 2020-02-06 | 2021-01-18 | CALCULATOR, LEARNING METHOD FOR DISCRIMINATOR AND ANALYSIS SYSTEM |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2020018575A JP7353198B2 (ja) | 2020-02-06 | 2020-02-06 | 計算機、識別器の学習方法、および分析システム |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| JP2021125003A JP2021125003A (ja) | 2021-08-30 |
| JP2021125003A5 JP2021125003A5 (https=) | 2022-07-27 |
| JP7353198B2 true JP7353198B2 (ja) | 2023-09-29 |
Family
ID=77199228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2020018575A Active JP7353198B2 (ja) | 2020-02-06 | 2020-02-06 | 計算機、識別器の学習方法、および分析システム |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US12536435B2 (https=) |
| EP (1) | EP4102454A4 (https=) |
| JP (1) | JP7353198B2 (https=) |
| CN (1) | CN114945940B (https=) |
| WO (1) | WO2021157330A1 (https=) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7463186B2 (ja) * | 2020-05-26 | 2024-04-08 | キヤノン株式会社 | 情報処理装置、情報処理方法及びプログラム |
| JP7709289B2 (ja) * | 2021-03-01 | 2025-07-16 | キヤノン株式会社 | 画像処理装置、画像処理方法 |
| US12188144B2 (en) * | 2022-01-31 | 2025-01-07 | Applied Materials, Inc. | Wafer immersion in semiconductor processing chambers |
| WO2023157094A1 (ja) * | 2022-02-15 | 2023-08-24 | 富士通株式会社 | モデル訓練プログラム、モデル訓練方法及び情報処理装置 |
| JP7771832B2 (ja) * | 2022-03-23 | 2025-11-18 | トヨタ自動車株式会社 | 情報処理装置、情報処理方法及びプログラム |
| WO2024047758A1 (ja) * | 2022-08-30 | 2024-03-07 | 富士通株式会社 | 訓練データ分布推定プログラム、装置、及び方法 |
| WO2024075251A1 (ja) * | 2022-10-06 | 2024-04-11 | 株式会社安川電機 | データ生成システム、産業機械、データ生成方法、およびデータ生成プログラム |
| WO2024185045A1 (ja) * | 2023-03-07 | 2024-09-12 | 日本電気株式会社 | データ生成装置、データ生成方法および記録媒体 |
| WO2025238808A1 (ja) * | 2024-05-16 | 2025-11-20 | 株式会社日立ハイテク | 情報処理装置、および情報処理方法 |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014178229A (ja) | 2013-03-15 | 2014-09-25 | Dainippon Screen Mfg Co Ltd | 教師データ作成方法、画像分類方法および画像分類装置 |
| JP2015191426A (ja) | 2014-03-28 | 2015-11-02 | セコム株式会社 | 学習データ生成装置 |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1185719A (ja) | 1997-09-03 | 1999-03-30 | Matsushita Electric Ind Co Ltd | パラメータ推定装置 |
| JP2004341959A (ja) * | 2003-05-16 | 2004-12-02 | Just Syst Corp | データ分類装置、データ分類方法およびその方法をコンピュータに実行させるプログラム |
| JP5214762B2 (ja) * | 2011-03-25 | 2013-06-19 | 株式会社東芝 | 認識装置、方法及びプログラム |
| JP6255296B2 (ja) * | 2014-03-31 | 2017-12-27 | セコム株式会社 | 対象識別装置 |
| US9961141B1 (en) * | 2015-06-29 | 2018-05-01 | Amazon Technologies, Inc. | Techniques and systems for tray-based storage and organization in automated data storage systems |
| JP6634635B2 (ja) * | 2015-11-18 | 2020-01-22 | 本田技研工業株式会社 | 識別装置、ロボットおよび識別方法 |
| JP6661398B2 (ja) | 2016-02-03 | 2020-03-11 | キヤノン株式会社 | 情報処理装置および情報処理方法 |
| JP6782679B2 (ja) * | 2016-12-06 | 2020-11-11 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカPanasonic Intellectual Property Corporation of America | 情報処理装置、情報処理方法及びプログラム |
| CN108229508B (zh) * | 2016-12-15 | 2022-01-04 | 富士通株式会社 | 用于训练图像处理装置的训练装置和训练方法 |
| CN107194336B (zh) * | 2017-05-11 | 2019-12-24 | 西安电子科技大学 | 基于半监督深度距离度量网络的极化sar图像分类方法 |
| JP6871807B2 (ja) * | 2017-05-31 | 2021-05-12 | 株式会社Screenホールディングス | 分類器構築方法、分類器および分類器構築装置 |
| CN107545275A (zh) * | 2017-07-27 | 2018-01-05 | 华南理工大学 | 重采样与代价敏感学习融合的不平衡数据集成分类方法 |
| JP7011904B2 (ja) | 2017-07-31 | 2022-01-27 | 株式会社日立ハイテク | 装置、試料における気泡の状態の判別方法、及び分析システム |
| JP7000766B2 (ja) * | 2017-09-19 | 2022-01-19 | 富士通株式会社 | 学習データ選択プログラム、学習データ選択方法、および、学習データ選択装置 |
| JP2019106089A (ja) * | 2017-12-14 | 2019-06-27 | キヤノン株式会社 | 情報処理装置、情報処理方法、コンピュータプログラム |
| JP7054436B2 (ja) * | 2017-12-14 | 2022-04-14 | オムロン株式会社 | 検出システム、情報処理装置、評価方法及びプログラム |
| CN108470187A (zh) * | 2018-02-26 | 2018-08-31 | 华南理工大学 | 一种基于扩充训练数据集的类别不平衡问题分类方法 |
| US20200012884A1 (en) * | 2018-07-03 | 2020-01-09 | General Electric Company | Classification based on annotation information |
| JP6829364B2 (ja) | 2018-07-31 | 2021-02-10 | 株式会社コナミデジタルエンタテインメント | ゲームシステム、及びそれに用いるコンピュータプログラム |
| JP2020046883A (ja) * | 2018-09-18 | 2020-03-26 | 株式会社東芝 | 分類装置、分類方法およびプログラム |
-
2020
- 2020-02-06 JP JP2020018575A patent/JP7353198B2/ja active Active
-
2021
- 2021-01-18 WO PCT/JP2021/001513 patent/WO2021157330A1/ja not_active Ceased
- 2021-01-18 US US17/795,291 patent/US12536435B2/en active Active
- 2021-01-18 EP EP21751391.0A patent/EP4102454A4/en active Pending
- 2021-01-18 CN CN202180008949.4A patent/CN114945940B/zh active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014178229A (ja) | 2013-03-15 | 2014-09-25 | Dainippon Screen Mfg Co Ltd | 教師データ作成方法、画像分類方法および画像分類装置 |
| JP2015191426A (ja) | 2014-03-28 | 2015-11-02 | セコム株式会社 | 学習データ生成装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| US20230072040A1 (en) | 2023-03-09 |
| US12536435B2 (en) | 2026-01-27 |
| WO2021157330A1 (ja) | 2021-08-12 |
| JP2021125003A (ja) | 2021-08-30 |
| EP4102454A1 (en) | 2022-12-14 |
| CN114945940B (zh) | 2026-04-07 |
| CN114945940A (zh) | 2022-08-26 |
| EP4102454A4 (en) | 2024-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7353198B2 (ja) | 計算機、識別器の学習方法、および分析システム | |
| JP7208480B2 (ja) | 学習プログラム、検出プログラム、学習装置、検出装置、学習方法および検出方法 | |
| US12217139B2 (en) | Transforming a trained artificial intelligence model into a trustworthy artificial intelligence model | |
| Webb et al. | On the application of ROC analysis to predict classification performance under varying class distributions | |
| CN112633310A (zh) | 具有改进的训练鲁棒性地对传感器数据进行分类的方法和系统 | |
| US20220004824A1 (en) | System and method to alter an image | |
| EP4375949A1 (en) | Object detection program, device, and machine learning model generation method | |
| CN111446002A (zh) | 一种基于人工智能的新型冠状病毒患者病况分类系统 | |
| JP2009186243A (ja) | 判別装置、判別方法及びプログラム | |
| US12361534B2 (en) | Engineering components | |
| US20240135159A1 (en) | System and method for a visual analytics framework for slice-based machine learn models | |
| US20240403653A1 (en) | Method and Apparatus | |
| CN115552462A (zh) | 显微镜中的图像分析方法 | |
| CN119540680A (zh) | 基于不确定性引导的神经网络测试数据集生成方法及系统 | |
| Chen et al. | Attack-inspired calibration loss for calibrating crack recognition | |
| Wille et al. | Are all marine species created equal? Performance disparities in underwater object detection | |
| CN114618167B (zh) | 反作弊检测模型构建方法以及反作弊检测方法 | |
| TW202345104A (zh) | 用於經標記影像的品質檢查之系統及方法 | |
| KR20230172154A (ko) | 인공지능을 이용한 이미지 객체를 분할 방법 및 장치 | |
| CN120950417B (zh) | 一种游戏运行系统更新后的稳定性和bug测试方法 | |
| Tian | Detect and repair errors for DNN-based software | |
| Byun | Manifold-based testing of machine learning systems | |
| US20260065637A1 (en) | Generalizable scene change detection method and system | |
| JP5636766B2 (ja) | 画像処理装置及び画像処理プログラム | |
| CN115439729B (zh) | 一种基于交替迭代优化的场景图生成装置和方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A523 Effective date: 20220719 |
|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20220719 |
|
| 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: 20230822 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20230919 |
|
| R150 | Certificate of patent or registration of utility model |
Ref document number: 7353198 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |