CN115917558A - 超参数调整装置、记录有超参数调整程序的非暂时性记录介质以及超参数调整程序 - Google Patents

超参数调整装置、记录有超参数调整程序的非暂时性记录介质以及超参数调整程序 Download PDF

Info

Publication number
CN115917558A
CN115917558A CN202080101959.8A CN202080101959A CN115917558A CN 115917558 A CN115917558 A CN 115917558A CN 202080101959 A CN202080101959 A CN 202080101959A CN 115917558 A CN115917558 A CN 115917558A
Authority
CN
China
Prior art keywords
hyperparameter
learning
neural network
performance
learned
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
CN202080101959.8A
Other languages
English (en)
Chinese (zh)
Inventor
河尻耕太郎
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.)
Aizos Co ltd
Original Assignee
Aizos Co ltd
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 Aizos Co ltd filed Critical Aizos Co ltd
Publication of CN115917558A publication Critical patent/CN115917558A/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
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
    • 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
    • G06N3/0499—Feedforward 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
    • 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
    • G06N3/08—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
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Physiology (AREA)
  • Genetics & Genomics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
CN202080101959.8A 2020-09-10 2020-09-10 超参数调整装置、记录有超参数调整程序的非暂时性记录介质以及超参数调整程序 Pending CN115917558A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/034354 WO2022054209A1 (ja) 2020-09-10 2020-09-10 ハイパーパラメータ調整装置、ハイパーパラメータ調整プログラムを記録した非一時的な記録媒体、及びハイパーパラメータ調整プログラム

Publications (1)

Publication Number Publication Date
CN115917558A true CN115917558A (zh) 2023-04-04

Family

ID=80631925

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080101959.8A Pending CN115917558A (zh) 2020-09-10 2020-09-10 超参数调整装置、记录有超参数调整程序的非暂时性记录介质以及超参数调整程序

Country Status (5)

Country Link
US (1) US12217189B2 (https=)
EP (1) EP4148623A4 (https=)
JP (1) JP7359493B2 (https=)
CN (1) CN115917558A (https=)
WO (1) WO2022054209A1 (https=)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020026327A1 (ja) * 2018-07-31 2020-02-06 日本電気株式会社 情報処理装置、制御方法、及びプログラム
US20230196125A1 (en) * 2021-12-16 2023-06-22 Capital One Services, Llc Techniques for ranked hyperparameter optimization
JP7199115B1 (ja) * 2021-12-17 2023-01-05 望 窪田 機械学習における分散学習
US12585960B2 (en) * 2022-02-17 2026-03-24 International Business Machines Corporation Dynamically tuning hyperparameters during ML model training
KR102710490B1 (ko) * 2023-10-27 2024-09-26 주식회사 카이어 사용자에 의해 선택된 데이터셋을 이용하여 인공지능모델을 자동으로 구축하는 방법 및 장치

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017154284A1 (ja) * 2016-03-09 2017-09-14 ソニー株式会社 情報処理方法および情報処理装置
US20180240041A1 (en) * 2017-02-22 2018-08-23 Sas Institute Inc. Distributed hyperparameter tuning system for machine learning
CN109242105A (zh) * 2018-08-17 2019-01-18 第四范式（北京）技术有限公司 机器学习模型中超参数的调优方法、装置、设备及介质
CN109242001A (zh) * 2018-08-09 2019-01-18 百度在线网络技术（北京）有限公司 图像数据处理方法、装置及可读存储介质
CN110443364A (zh) * 2019-06-21 2019-11-12 深圳大学 一种深度神经网络多任务超参数优化方法及装置
US20200143243A1 (en) * 2018-11-01 2020-05-07 Cognizant Technology Solutions U.S. Corporation Multiobjective Coevolution of Deep Neural Network Architectures

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS59192647A (ja) 1983-04-15 1984-11-01 Kokusan Kinzoku Kogyo Co Ltd キ−レスステアリングロツク
JP6351671B2 (ja) 2016-08-26 2018-07-04 株式会社 ディー・エヌ・エー ニューロエボリューションを用いたニューラルネットワークの構造及びパラメータ調整のためのプログラム、システム、及び方法
JP6523379B2 (ja) 2017-07-25 2019-05-29 ファナック株式会社 情報処理装置
US11120368B2 (en) * 2017-09-27 2021-09-14 Oracle International Corporation Scalable and efficient distributed auto-tuning of machine learning and deep learning models
JP2020123292A (ja) 2019-01-31 2020-08-13 パナソニックＩｐマネジメント株式会社 ニューラルネットワークの評価方法、ニューラルネットワークの生成方法、プログラム及び評価システム
US20210019615A1 (en) * 2019-07-18 2021-01-21 International Business Machines Corporation Extraction of entities having defined lengths of text spans
CN110633797B (zh) 2019-09-11 2022-12-02 北京百度网讯科技有限公司 网络模型结构的搜索方法、装置以及电子设备
US11669735B2 (en) * 2020-01-23 2023-06-06 Vmware, Inc. System and method for automatically generating neural networks for anomaly detection in log data from distributed systems

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017154284A1 (ja) * 2016-03-09 2017-09-14 ソニー株式会社 情報処理方法および情報処理装置
US20180365557A1 (en) * 2016-03-09 2018-12-20 Sony Corporation Information processing method and information processing apparatus
US20180240041A1 (en) * 2017-02-22 2018-08-23 Sas Institute Inc. Distributed hyperparameter tuning system for machine learning
CN109242001A (zh) * 2018-08-09 2019-01-18 百度在线网络技术（北京）有限公司 图像数据处理方法、装置及可读存储介质
CN109242105A (zh) * 2018-08-17 2019-01-18 第四范式（北京）技术有限公司 机器学习模型中超参数的调优方法、装置、设备及介质
US20200143243A1 (en) * 2018-11-01 2020-05-07 Cognizant Technology Solutions U.S. Corporation Multiobjective Coevolution of Deep Neural Network Architectures
CN110443364A (zh) * 2019-06-21 2019-11-12 深圳大学 一种深度神经网络多任务超参数优化方法及装置

Also Published As

Publication number Publication date
JPWO2022054209A1 (https=) 2022-03-17
WO2022054209A1 (ja) 2022-03-17
EP4148623A4 (en) 2024-02-07
US12217189B2 (en) 2025-02-04
US20230214668A1 (en) 2023-07-06
JP7359493B2 (ja) 2023-10-11
EP4148623A1 (en) 2023-03-15

Similar Documents

Publication Publication Date Title
CN115917558A (zh) 超参数调整装置、记录有超参数调整程序的非暂时性记录介质以及超参数调整程序
Kiziloz et al. Novel multiobjective TLBO algorithms for the feature subset selection problem
Kulkarni et al. Pruning of random forest classifiers: A survey and future directions
Goudet et al. Causal generative neural networks
US11914672B2 (en) Method of neural architecture search using continuous action reinforcement learning
Xiang et al. Stable local interpretable model-agnostic explanations based on a variational autoencoder: X. Xiang et al.
Biswas et al. A Bi-objective RNN model to reconstruct gene regulatory network: a modified multi-objective simulated annealing approach
CN118132914A (zh) 确定影响低压台区线损率的主要特征因子的方法
CN119539041A (zh) 一种基于蒙特卡洛树的自适应因果发现方法及设备
CN110555530A (zh) 一种基于分布式的大规模基因调控网络构建方法
Kowalski et al. Feature selection for regression tasks base on explainable artificial intelligence procedures
Aldeia et al. A parametric study of interaction-transformation evolutionary algorithm for symbolic regression
Zeng et al. Improved Population-Based Incremental Learning of Bayesian Networks with partly known structure and parallel computing
EP4038552A1 (en) Optimizing reservoir computers for hardware implementation
Kavipriya et al. Adaptive Weight Deep Convolutional Neural Network (AWDCNN) Classifier for Predicting Student's Performance in Job Placement Process
CN113837474A (zh) 区域土壤重金属污染指数预测方法及装置
Djordjilović et al. An empirical comparison of popular structure learning algorithms with a view to gene network inference
US20240419960A1 (en) Backpropagation for discrete variables
Chandrappa et al. Prediction of autism spectrum disorder based on machine learning approach
Park et al. Multivariate L\'evy Adaptive B-Spline Regression
Wilson et al. Neuromodulated learning in deep neural networks
Carter Deep learning for robust meta-analytic estimation
Liu et al. An evaluation of hyperparameter tuning methods in SVM
Overmann et al. Benchmarking precision matrix estimation methods for differential co-expression network analysis
Assiroj et al. Comparing CART and C5. 0 Algorithm Performance of Human Development Index

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