WO2019067960A1 - Développement agressif à l'aide de générateurs coopératifs - Google Patents
Développement agressif à l'aide de générateurs coopératifs Download PDFInfo
- Publication number
- WO2019067960A1 WO2019067960A1 PCT/US2018/053519 US2018053519W WO2019067960A1 WO 2019067960 A1 WO2019067960 A1 WO 2019067960A1 US 2018053519 W US2018053519 W US 2018053519W WO 2019067960 A1 WO2019067960 A1 WO 2019067960A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- computer system
- data
- machine learning
- classifier
- neural network
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
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)
- Hardware Redundancy (AREA)
Abstract
L'invention concerne divers systèmes et procédés permettant d'améliorer le développement agressif de systèmes d'apprentissage machine. Au cours de l'apprentissage machine, un compromis doit être trouvé entre permettre à un système d'apprentissage machine d'apprendre autant qu'il peut des données d'entraînement et obtenir un surapprentissage sur les données d'entraînement. Ce compromis est important car le surapprentissage provoque habituellement la diminution des performances sur les nouvelles données. Toutefois, divers systèmes et procédés peuvent être utilisés pour séparer le processus d'apprentissage détaillé et d'acquisition des connaissances et le processus d'imposition de restrictions et de lissage des estimations, ce qui permet à des systèmes d'apprentissage machine d'apprendre de manière agressive des données d'entraînement, tout en atténuant les effets de surapprentissage sur les données d'entraînement.
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP18862297.1A EP3688678A4 (fr) | 2017-09-28 | 2018-09-28 | Développement agressif à l'aide de générateurs coopératifs |
US16/645,710 US20200285939A1 (en) | 2017-09-28 | 2018-09-28 | Aggressive development with cooperative generators |
CN201880076808.4A CN111542843A (zh) | 2017-09-28 | 2018-09-28 | 利用协作生成器积极开发 |
US16/901,608 US11410050B2 (en) | 2017-09-28 | 2020-06-15 | Imitation training for machine learning systems with synthetic data generators |
US17/810,778 US11531900B2 (en) | 2017-09-28 | 2022-07-05 | Imitation learning for machine learning systems with synthetic data generators |
US17/815,851 US11687788B2 (en) | 2017-09-28 | 2022-07-28 | Generating synthetic data examples as interpolation of two data examples that is linear in the space of relative scores |
US18/196,855 US20230289611A1 (en) | 2017-09-28 | 2023-05-12 | Locating a decision boundary for complex classifier |
Applications Claiming Priority (8)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201762564754P | 2017-09-28 | 2017-09-28 | |
US62/564,754 | 2017-09-28 | ||
PCT/US2018/051069 WO2019067236A1 (fr) | 2017-09-28 | 2018-09-14 | Mélange de modèles de générateurs |
USPCT/US2018/051069 | 2018-09-14 | ||
PCT/US2018/051332 WO2019067248A1 (fr) | 2017-09-28 | 2018-09-17 | Estimation de quantité de dégradation avec un objectif de régression en apprentissage profond |
USPCT/US2018/051332 | 2018-09-17 | ||
USPCT/US2018/051683 | 2018-09-19 | ||
PCT/US2018/051683 WO2019067281A1 (fr) | 2017-09-28 | 2018-09-19 | Mémoire auto-associative robuste avec réseau de neurones bouclé |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2018/051683 Continuation WO2019067281A1 (fr) | 2017-09-28 | 2018-09-19 | Mémoire auto-associative robuste avec réseau de neurones bouclé |
Related Child Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/645,710 A-371-Of-International US20200285939A1 (en) | 2017-09-28 | 2018-09-28 | Aggressive development with cooperative generators |
US16/901,608 Continuation US11410050B2 (en) | 2017-09-28 | 2020-06-15 | Imitation training for machine learning systems with synthetic data generators |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019067960A1 true WO2019067960A1 (fr) | 2019-04-04 |
Family
ID=65902702
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2018/053519 WO2019067960A1 (fr) | 2017-09-28 | 2018-09-28 | Développement agressif à l'aide de générateurs coopératifs |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2019067960A1 (fr) |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110133146A (zh) * | 2019-05-28 | 2019-08-16 | 国网上海市电力公司 | 一种考虑不平衡数据样本的变压器故障诊断方法及系统 |
CN110739030A (zh) * | 2019-09-16 | 2020-01-31 | 北京化工大学 | 一种乙烯生产过程小样本的软测量方法 |
US10832137B2 (en) | 2018-01-30 | 2020-11-10 | D5Ai Llc | Merging multiple nodal networks |
EP3739515A1 (fr) * | 2019-05-16 | 2020-11-18 | Robert Bosch GmbH | Détermination d'un masque de perturbation pour un modèle de classification |
US10885470B2 (en) | 2017-06-26 | 2021-01-05 | D5Ai Llc | Selective training for decorrelation of errors |
CN112215251A (zh) * | 2019-07-09 | 2021-01-12 | 百度(美国)有限责任公司 | 用于使用基于特征分散的对抗训练来防御对抗攻击的系统和方法 |
US10922587B2 (en) | 2018-07-03 | 2021-02-16 | D5Ai Llc | Analyzing and correcting vulnerabilities in neural networks |
US10929757B2 (en) | 2018-01-30 | 2021-02-23 | D5Ai Llc | Creating and training a second nodal network to perform a subtask of a primary nodal network |
CN112416293A (zh) * | 2020-11-24 | 2021-02-26 | 深圳市人工智能与机器人研究院 | 一种神经网络增强方法、系统及其应用 |
US10956818B2 (en) | 2017-06-08 | 2021-03-23 | D5Ai Llc | Data splitting by gradient direction for neural networks |
US20210125005A1 (en) * | 2019-10-23 | 2021-04-29 | De-Identification Ltd. | System and method for protection and detection of adversarial attacks against a classifier |
US11003982B2 (en) | 2017-06-27 | 2021-05-11 | D5Ai Llc | Aligned training of deep networks |
WO2021089570A1 (fr) * | 2019-11-08 | 2021-05-14 | Koninklijke Philips N.V. | Combinaison de sorties de modèle en une sortie de modèle combinée |
US11010670B2 (en) | 2018-08-27 | 2021-05-18 | D5Ai Llc | Building a deep neural network with diverse strata |
US11037059B2 (en) | 2018-08-31 | 2021-06-15 | D5Ai Llc | Self-supervised back propagation for deep learning |
CN112990424A (zh) * | 2019-12-17 | 2021-06-18 | 杭州海康威视数字技术股份有限公司 | 神经网络模型训练的方法和装置 |
US11074502B2 (en) | 2018-08-23 | 2021-07-27 | D5Ai Llc | Efficiently building deep neural networks |
CN113343991A (zh) * | 2021-08-02 | 2021-09-03 | 四川新网银行股份有限公司 | 一种特征内增强的弱监督学习方法 |
WO2021194516A1 (fr) * | 2020-03-23 | 2021-09-30 | D5Ai Llc | Partage de connaissances de nœud à nœud dépendant de données par régularisation en apprentissage profond |
EP3905139A1 (fr) * | 2020-04-30 | 2021-11-03 | Stradvision, Inc. | Procédé permettant d'effectuer un apprentissage continu sur le classificateur d'un client capable de classer des images au moyen d'un serveur d'apprentissage continu et serveur d'apprentissage continu l'utilisant |
US11195097B2 (en) | 2018-07-16 | 2021-12-07 | D5Ai Llc | Building ensembles for deep learning by parallel data splitting |
CN113822437A (zh) * | 2020-06-18 | 2021-12-21 | 辉达公司 | 深度分层的变分自动编码器 |
US20220060235A1 (en) * | 2020-08-18 | 2022-02-24 | Qualcomm Incorporated | Federated learning for client-specific neural network parameter generation for wireless communication |
US11270188B2 (en) | 2017-09-28 | 2022-03-08 | D5Ai Llc | Joint optimization of ensembles in deep learning |
US11295210B2 (en) | 2017-06-05 | 2022-04-05 | D5Ai Llc | Asynchronous agents with learning coaches and structurally modifying deep neural networks without performance degradation |
US11321612B2 (en) | 2018-01-30 | 2022-05-03 | D5Ai Llc | Self-organizing partially ordered networks and soft-tying learned parameters, such as connection weights |
US11410050B2 (en) | 2017-09-28 | 2022-08-09 | D5Ai Llc | Imitation training for machine learning systems with synthetic data generators |
US11501164B2 (en) | 2018-08-09 | 2022-11-15 | D5Ai Llc | Companion analysis network in deep learning |
US11640552B2 (en) | 2019-10-01 | 2023-05-02 | International Business Machines Corporation | Two stage training to obtain a best deep learning model with efficient use of computing resources |
US11676026B2 (en) | 2018-06-29 | 2023-06-13 | D5Ai Llc | Using back propagation computation as data |
CN116843985A (zh) * | 2023-09-01 | 2023-10-03 | 中国地质调查局武汉地质调查中心 | 一种基于多重一致性约束的矿区图像半监督分类方法 |
US11836600B2 (en) | 2020-08-20 | 2023-12-05 | D5Ai Llc | Targeted incremental growth with continual learning in deep neural networks |
US11847559B2 (en) | 2020-03-04 | 2023-12-19 | HCL America, Inc. | Modifying data cleansing techniques for training and validating an artificial neural network model |
CN112990424B (zh) * | 2019-12-17 | 2024-05-10 | 杭州海康威视数字技术股份有限公司 | 神经网络模型训练的方法和装置 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020008657A1 (en) * | 1993-12-21 | 2002-01-24 | Aubrey B. Poore Jr | Method and system for tracking multiple regional objects by multi-dimensional relaxation |
US20040042650A1 (en) * | 2002-08-30 | 2004-03-04 | Lockheed Martin Corporation | Binary optical neural network classifiers for pattern recognition |
US20050169529A1 (en) * | 2004-02-03 | 2005-08-04 | Yuri Owechko | Active learning system for object fingerprinting |
US20050216426A1 (en) * | 2001-05-18 | 2005-09-29 | Weston Jason Aaron E | Methods for feature selection in a learning machine |
US20160224903A1 (en) * | 2015-01-29 | 2016-08-04 | Qualcomm Incorporated | Hyper-parameter selection for deep convolutional networks |
US20160247326A1 (en) * | 2015-02-24 | 2016-08-25 | Xerox Corporation | Method and system for simulating users in the context of a parking lot based on the automatic learning of a user choice decision function from historical data considering multiple user behavior profiles |
US20160379132A1 (en) * | 2015-06-23 | 2016-12-29 | Adobe Systems Incorporated | Collaborative feature learning from social media |
-
2018
- 2018-09-28 WO PCT/US2018/053519 patent/WO2019067960A1/fr unknown
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020008657A1 (en) * | 1993-12-21 | 2002-01-24 | Aubrey B. Poore Jr | Method and system for tracking multiple regional objects by multi-dimensional relaxation |
US20050216426A1 (en) * | 2001-05-18 | 2005-09-29 | Weston Jason Aaron E | Methods for feature selection in a learning machine |
US20040042650A1 (en) * | 2002-08-30 | 2004-03-04 | Lockheed Martin Corporation | Binary optical neural network classifiers for pattern recognition |
US20050169529A1 (en) * | 2004-02-03 | 2005-08-04 | Yuri Owechko | Active learning system for object fingerprinting |
US20160224903A1 (en) * | 2015-01-29 | 2016-08-04 | Qualcomm Incorporated | Hyper-parameter selection for deep convolutional networks |
US20160247326A1 (en) * | 2015-02-24 | 2016-08-25 | Xerox Corporation | Method and system for simulating users in the context of a parking lot based on the automatic learning of a user choice decision function from historical data considering multiple user behavior profiles |
US20160379132A1 (en) * | 2015-06-23 | 2016-12-29 | Adobe Systems Incorporated | Collaborative feature learning from social media |
Non-Patent Citations (1)
Title |
---|
See also references of EP3688678A4 * |
Cited By (51)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11790235B2 (en) | 2017-06-05 | 2023-10-17 | D5Ai Llc | Deep neural network with compound node functioning as a detector and rejecter |
US11562246B2 (en) | 2017-06-05 | 2023-01-24 | D5Ai Llc | Asynchronous agents with learning coaches and structurally modifying deep neural networks without performance degradation |
US11392832B2 (en) | 2017-06-05 | 2022-07-19 | D5Ai Llc | Asynchronous agents with learning coaches and structurally modifying deep neural networks without performance degradation |
US11295210B2 (en) | 2017-06-05 | 2022-04-05 | D5Ai Llc | Asynchronous agents with learning coaches and structurally modifying deep neural networks without performance degradation |
US10956818B2 (en) | 2017-06-08 | 2021-03-23 | D5Ai Llc | Data splitting by gradient direction for neural networks |
US10885470B2 (en) | 2017-06-26 | 2021-01-05 | D5Ai Llc | Selective training for decorrelation of errors |
US11003982B2 (en) | 2017-06-27 | 2021-05-11 | D5Ai Llc | Aligned training of deep networks |
US11531900B2 (en) | 2017-09-28 | 2022-12-20 | D5Ai Llc | Imitation learning for machine learning systems with synthetic data generators |
US11410050B2 (en) | 2017-09-28 | 2022-08-09 | D5Ai Llc | Imitation training for machine learning systems with synthetic data generators |
US11270188B2 (en) | 2017-09-28 | 2022-03-08 | D5Ai Llc | Joint optimization of ensembles in deep learning |
US11010671B2 (en) | 2018-01-30 | 2021-05-18 | D5Ai Llc | Iterative training of a nodal network with data influence weights |
US11151455B2 (en) | 2018-01-30 | 2021-10-19 | D5Ai Llc | Counter-tying nodes of a nodal network |
US11748624B2 (en) | 2018-01-30 | 2023-09-05 | D5Ai Llc | Evaluating the value of connecting a selected pair of unconnected nodes of a nodal network |
US10832137B2 (en) | 2018-01-30 | 2020-11-10 | D5Ai Llc | Merging multiple nodal networks |
US11461655B2 (en) | 2018-01-30 | 2022-10-04 | D5Ai Llc | Self-organizing partially ordered networks |
US11321612B2 (en) | 2018-01-30 | 2022-05-03 | D5Ai Llc | Self-organizing partially ordered networks and soft-tying learned parameters, such as connection weights |
US10929757B2 (en) | 2018-01-30 | 2021-02-23 | D5Ai Llc | Creating and training a second nodal network to perform a subtask of a primary nodal network |
US11087217B2 (en) | 2018-01-30 | 2021-08-10 | D5Ai Llc | Directly connecting nodes of different copies on an unrolled recursive neural network |
US11093830B2 (en) | 2018-01-30 | 2021-08-17 | D5Ai Llc | Stacking multiple nodal networks |
US11676026B2 (en) | 2018-06-29 | 2023-06-13 | D5Ai Llc | Using back propagation computation as data |
US10922587B2 (en) | 2018-07-03 | 2021-02-16 | D5Ai Llc | Analyzing and correcting vulnerabilities in neural networks |
US11195097B2 (en) | 2018-07-16 | 2021-12-07 | D5Ai Llc | Building ensembles for deep learning by parallel data splitting |
US11501164B2 (en) | 2018-08-09 | 2022-11-15 | D5Ai Llc | Companion analysis network in deep learning |
US11074502B2 (en) | 2018-08-23 | 2021-07-27 | D5Ai Llc | Efficiently building deep neural networks |
US11010670B2 (en) | 2018-08-27 | 2021-05-18 | D5Ai Llc | Building a deep neural network with diverse strata |
US11037059B2 (en) | 2018-08-31 | 2021-06-15 | D5Ai Llc | Self-supervised back propagation for deep learning |
EP3739515A1 (fr) * | 2019-05-16 | 2020-11-18 | Robert Bosch GmbH | Détermination d'un masque de perturbation pour un modèle de classification |
CN110133146A (zh) * | 2019-05-28 | 2019-08-16 | 国网上海市电力公司 | 一种考虑不平衡数据样本的变压器故障诊断方法及系统 |
CN112215251A (zh) * | 2019-07-09 | 2021-01-12 | 百度(美国)有限责任公司 | 用于使用基于特征分散的对抗训练来防御对抗攻击的系统和方法 |
CN110739030A (zh) * | 2019-09-16 | 2020-01-31 | 北京化工大学 | 一种乙烯生产过程小样本的软测量方法 |
CN110739030B (zh) * | 2019-09-16 | 2023-09-01 | 北京化工大学 | 一种乙烯生产过程小样本的软测量方法 |
US11640552B2 (en) | 2019-10-01 | 2023-05-02 | International Business Machines Corporation | Two stage training to obtain a best deep learning model with efficient use of computing resources |
US11762998B2 (en) * | 2019-10-23 | 2023-09-19 | De-Identification Ltd. | System and method for protection and detection of adversarial attacks against a classifier |
US20210125005A1 (en) * | 2019-10-23 | 2021-04-29 | De-Identification Ltd. | System and method for protection and detection of adversarial attacks against a classifier |
WO2021089570A1 (fr) * | 2019-11-08 | 2021-05-14 | Koninklijke Philips N.V. | Combinaison de sorties de modèle en une sortie de modèle combinée |
CN112990424A (zh) * | 2019-12-17 | 2021-06-18 | 杭州海康威视数字技术股份有限公司 | 神经网络模型训练的方法和装置 |
CN112990424B (zh) * | 2019-12-17 | 2024-05-10 | 杭州海康威视数字技术股份有限公司 | 神经网络模型训练的方法和装置 |
US11847559B2 (en) | 2020-03-04 | 2023-12-19 | HCL America, Inc. | Modifying data cleansing techniques for training and validating an artificial neural network model |
WO2021194516A1 (fr) * | 2020-03-23 | 2021-09-30 | D5Ai Llc | Partage de connaissances de nœud à nœud dépendant de données par régularisation en apprentissage profond |
US11741340B2 (en) | 2020-03-23 | 2023-08-29 | D5Ai Llc | Data-dependent node-to-node knowledge sharing by regularization in deep learning |
WO2021221254A1 (fr) * | 2020-04-30 | 2021-11-04 | StradVision, Inc. | Procédé pour effectuer à l'aide d'un serveur d'apprentissage continu un apprentissage continu sur un classifieur dans un client apte à classifier des images, et serveur d'apprentissage continu l'utilisant |
EP3905139A1 (fr) * | 2020-04-30 | 2021-11-03 | Stradvision, Inc. | Procédé permettant d'effectuer un apprentissage continu sur le classificateur d'un client capable de classer des images au moyen d'un serveur d'apprentissage continu et serveur d'apprentissage continu l'utilisant |
CN113822437A (zh) * | 2020-06-18 | 2021-12-21 | 辉达公司 | 深度分层的变分自动编码器 |
US20220060235A1 (en) * | 2020-08-18 | 2022-02-24 | Qualcomm Incorporated | Federated learning for client-specific neural network parameter generation for wireless communication |
US11909482B2 (en) * | 2020-08-18 | 2024-02-20 | Qualcomm Incorporated | Federated learning for client-specific neural network parameter generation for wireless communication |
US11836600B2 (en) | 2020-08-20 | 2023-12-05 | D5Ai Llc | Targeted incremental growth with continual learning in deep neural networks |
US11948063B2 (en) | 2020-08-20 | 2024-04-02 | D5Ai Llc | Improving a deep neural network with node-to-node relationship regularization |
CN112416293A (zh) * | 2020-11-24 | 2021-02-26 | 深圳市人工智能与机器人研究院 | 一种神经网络增强方法、系统及其应用 |
CN113343991A (zh) * | 2021-08-02 | 2021-09-03 | 四川新网银行股份有限公司 | 一种特征内增强的弱监督学习方法 |
CN116843985A (zh) * | 2023-09-01 | 2023-10-03 | 中国地质调查局武汉地质调查中心 | 一种基于多重一致性约束的矿区图像半监督分类方法 |
CN116843985B (zh) * | 2023-09-01 | 2023-11-17 | 中国地质调查局武汉地质调查中心 | 一种基于多重一致性约束的矿区图像半监督分类方法 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11531900B2 (en) | Imitation learning for machine learning systems with synthetic data generators | |
WO2019067960A1 (fr) | Développement agressif à l'aide de générateurs coopératifs | |
Gonzalez et al. | Improved training speed, accuracy, and data utilization through loss function optimization | |
Yang et al. | On hyperparameter optimization of machine learning algorithms: Theory and practice | |
Hu et al. | Empirical bayes transductive meta-learning with synthetic gradients | |
Huang et al. | A deep reinforcement learning based long-term recommender system | |
Rokach | Taxonomy for characterizing ensemble methods in classification tasks: A review and annotated bibliography | |
Chen et al. | Experiments with repeating weighted boosting search for optimization signal processing applications | |
Vadimovich et al. | Self-adjusted evolutionary algorithms based approach for automated design of fuzzy logic systems | |
Bohdal et al. | Meta-calibration: Learning of model calibration using differentiable expected calibration error | |
Duch et al. | Meta-learning: searching in the model space | |
KR20220014744A (ko) | 강화 학습을 기반으로 한 데이터 전처리 시스템 및 방법 | |
Li | Regularized adaptation: Theory, algorithms and applications | |
Schilling et al. | Joint model choice and hyperparameter optimization with factorized multilayer perceptrons | |
Berral-García | When and how to apply Statistics, Machine Learning and Deep Learning techniques | |
CN116561614A (zh) | 一种基于元学习的小样本数据处理系统 | |
Upal et al. | Comparison of unsupervised classifiers | |
Zhu et al. | Automated Machine Learning and Meta-Learning for Multimedia | |
Biehl | Supervised Learning–An Introduction | |
Ali | Meta-level learning for the effective reduction of model search space. | |
Santana et al. | Bio-inspired meta-heuristic as feature selector in ensemble systems: A comparative analysis | |
Ororbia | Brain-inspired machine intelligence: A survey of neurobiologically-plausible credit assignment | |
Olmo et al. | Binary and multiclass imbalanced classification using multi-objective ant programming | |
Plested | Beyond binary hyperparameters in deep transfer learning for image classification | |
Rosenbaum | Dynamic composition of functions for modular learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18862297 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2018862297 Country of ref document: EP Effective date: 20200428 |