JP7464114B2 - 識別装置、識別方法及び記録媒体 - Google Patents

識別装置、識別方法及び記録媒体 Download PDF

Info

Publication number
JP7464114B2
JP7464114B2 JP2022518529A JP2022518529A JP7464114B2 JP 7464114 B2 JP7464114 B2 JP 7464114B2 JP 2022518529 A JP2022518529 A JP 2022518529A JP 2022518529 A JP2022518529 A JP 2022518529A JP 7464114 B2 JP7464114 B2 JP 7464114B2
Authority
JP
Japan
Prior art keywords
index value
classification
class
input data
objective function
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
JP2022518529A
Other languages
English (en)
Japanese (ja)
Other versions
JPWO2021220450A5 (https=
JPWO2021220450A1 (https=
Inventor
大輝 宮川
章記 海老原
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.)
NEC Corp
Original Assignee
NEC Corp
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 NEC Corp filed Critical NEC Corp
Publication of JPWO2021220450A1 publication Critical patent/JPWO2021220450A1/ja
Publication of JPWO2021220450A5 publication Critical patent/JPWO2021220450A5/ja
Application granted granted Critical
Publication of JP7464114B2 publication Critical patent/JP7464114B2/ja
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
    • 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
    • G06N3/08—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
    • G06N3/044—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
    • G06N3/08—Learning methods
    • G06N3/09—Supervised learning

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)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)
JP2022518529A 2020-04-30 2020-04-30 識別装置、識別方法及び記録媒体 Active JP7464114B2 (ja)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/018236 WO2021220450A1 (ja) 2020-04-30 2020-04-30 識別装置、識別方法及び記録媒体

Publications (3)

Publication Number Publication Date
JPWO2021220450A1 JPWO2021220450A1 (https=) 2021-11-04
JPWO2021220450A5 JPWO2021220450A5 (https=) 2023-01-23
JP7464114B2 true JP7464114B2 (ja) 2024-04-09

Family

ID=78331882

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2022518529A Active JP7464114B2 (ja) 2020-04-30 2020-04-30 識別装置、識別方法及び記録媒体

Country Status (3)

Country Link
US (1) US20220245519A1 (https=)
JP (1) JP7464114B2 (https=)
WO (1) WO2021220450A1 (https=)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12367387B2 (en) * 2020-06-05 2025-07-22 Deepmind Technologies Limited Neural network optimization using curvature estimates based on recent gradients
WO2025069242A1 (ja) * 2023-09-27 2025-04-03 日本電気株式会社 情報処理装置、情報処理方法、及び記録媒体

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019049688A1 (ja) 2017-09-06 2019-03-14 日本電信電話株式会社 異常音検知装置、異常モデル学習装置、異常検知装置、異常音検知方法、異常音生成装置、異常データ生成装置、異常音生成方法、およびプログラム
US20190095799A1 (en) 2017-08-18 2019-03-28 University Of Southern California Optimally stopped optimization systems and methods
JP2019164618A (ja) 2018-03-20 2019-09-26 株式会社東芝 信号処理装置、信号処理方法およびプログラム

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190095799A1 (en) 2017-08-18 2019-03-28 University Of Southern California Optimally stopped optimization systems and methods
WO2019049688A1 (ja) 2017-09-06 2019-03-14 日本電信電話株式会社 異常音検知装置、異常モデル学習装置、異常検知装置、異常音検知方法、異常音生成装置、異常データ生成装置、異常音生成方法、およびプログラム
JP2019164618A (ja) 2018-03-20 2019-09-26 株式会社東芝 信号処理装置、信号処理方法およびプログラム

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Russwurm, M., et al.，End-to-end learning for early classification of time series.[online]，arXiv，2019年01月30日，[検索日 2020.09.25], Internet: <URL:https://arxiv.org/pdf/1901.10681.pdf>
Wang, W., et al.，Earliness-aware deep convolutional networks for early time series classification. [online]，arXiv，2016年11月14日，[検索日 2020.09.25], Internet: <URL:https://arxiv.org/pdf/1611.04578.pdf>

Also Published As

Publication number Publication date
US20220245519A1 (en) 2022-08-04
WO2021220450A1 (ja) 2021-11-04
JPWO2021220450A1 (https=) 2021-11-04

Similar Documents

Publication Publication Date Title
CN116635866B (zh) 用于挖掘少数类数据样本以训练神经网络的方法和系统
US11977625B2 (en) Using multimodal model consistency to detect adversarial attacks
CN106548210B (zh) 基于机器学习模型训练的信贷用户分类方法及装置
CN111310814A (zh) 利用不平衡正负样本对业务预测模型训练的方法及装置
CN111310915A (zh) 一种面向强化学习的数据异常检测防御方法
JP7688464B2 (ja) 敵対的補間バックドア検出
US12572941B2 (en) Multi-model system for electronic transaction authorization and fraud detection
CN119624465B (zh) 基于ai驱动的异常交易智能监测与分析系统及方法
WO2020247200A1 (en) Likelihood ratios for out-of-distribution detection
CN112116957A (zh) 基于小样本的疾病亚型预测方法、系统、装置及介质
CN110335160B (zh) 一种基于分组和注意力改进Bi-GRU的就医迁移行为预测方法及系统
KR102308752B1 (ko) 객체 추적 방법 및 장치
CN108475425A (zh) 图像处理装置、图像处理方法及图像处理程序
JP7464114B2 (ja) 識別装置、識別方法及び記録媒体
Agarwal et al. A comprehensive analysis of classical machine learning and modern deep learning methodologies
CN115953430B (zh) 基于改进的批量样本损失函数的视频单目标跟踪方法及系统
CN115936104A (zh) 用于训练机器学习模型的方法和装置
US20230267349A1 (en) Smart training and smart deployment of machine learning models
Gan et al. Deep Reinforcement Learning and Dempster-Shafer Theory: A Unified Approach to Imbalanced Classification
Zhou et al. Sepsyn-olcp: An online learning-based framework for early sepsis prediction with uncertainty quantification using conformal prediction
CN115455408A (zh) 一种网络空间推演与安全评估方法及装置
Yuvarajan et al. A Comparison of Machine Learning Techniques for Survival Prediction in Breast Cancer Gene Expression Data
CN121074532B (zh) 抗结构噪声图开集节点分类方法、装置、电子设备及介质
CN121391894B (en) Dual-correction-based semi-supervised medical image segmentation method
Kurz et al. Isolating cost drivers in interstitial lung disease treatment using nonparametric Bayesian methods

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20221027

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20221027

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20230919

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20231031

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20231212

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20240206

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: 20240227

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20240311

R150 Certificate of patent or registration of utility model

Ref document number: 7464114

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150