CN117057413A - 强化学习模型微调方法、装置、计算机设备及存储介质 - Google Patents
强化学习模型微调方法、装置、计算机设备及存储介质 Download PDFInfo
- Publication number
- CN117057413A CN117057413A CN202311259451.2A CN202311259451A CN117057413A CN 117057413 A CN117057413 A CN 117057413A CN 202311259451 A CN202311259451 A CN 202311259451A CN 117057413 A CN117057413 A CN 117057413A
- Authority
- CN
- China
- Prior art keywords
- model
- fine tuning
- labeling
- result
- reinforcement learning
- 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.)
- Granted
Links
- 230000002787 reinforcement Effects 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000002372 labelling Methods 0.000 claims abstract description 128
- 238000012549 training Methods 0.000 claims abstract description 75
- 238000012544 monitoring process Methods 0.000 claims abstract description 25
- 238000004821 distillation Methods 0.000 claims abstract description 23
- 238000012360 testing method Methods 0.000 claims abstract description 17
- 230000007547 defect Effects 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000009966 trimming Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 27
- 230000000007 visual effect Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 22
- 239000013598 vector Substances 0.000 claims description 19
- 230000005540 biological transmission Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000015556 catabolic process Effects 0.000 abstract description 8
- 238000006731 degradation reaction Methods 0.000 abstract description 8
- 238000013461 design Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 12
- 238000005457 optimization Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000013140 knowledge distillation Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06N3/092—Reinforcement learning
-
- 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
- G06N3/096—Transfer learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311259451.2A CN117057413B (zh) | 2023-09-27 | 2023-09-27 | 强化学习模型微调方法、装置、计算机设备及存储介质 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311259451.2A CN117057413B (zh) | 2023-09-27 | 2023-09-27 | 强化学习模型微调方法、装置、计算机设备及存储介质 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117057413A true CN117057413A (zh) | 2023-11-14 |
CN117057413B CN117057413B (zh) | 2024-03-15 |
Family
ID=88669474
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311259451.2A Active CN117057413B (zh) | 2023-09-27 | 2023-09-27 | 强化学习模型微调方法、装置、计算机设备及存储介质 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117057413B (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117292119A (zh) * | 2023-11-24 | 2023-12-26 | 国网智能科技股份有限公司 | 一种输电多尺度目标检测方法及系统 |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109902371A (zh) * | 2019-02-19 | 2019-06-18 | 校宝在线(杭州)科技股份有限公司 | 一种基于深度强化学习的智能排课方法 |
CN112115724A (zh) * | 2020-07-23 | 2020-12-22 | 云知声智能科技股份有限公司 | 一种多领域神经网络在垂直领域微调的优化方法及系统 |
CN113076950A (zh) * | 2021-04-01 | 2021-07-06 | 安徽酷哇机器人有限公司 | 一种基于深度强化学习的图像数据自动化标注方法及系统 |
CN113947196A (zh) * | 2021-10-25 | 2022-01-18 | 中兴通讯股份有限公司 | 网络模型训练方法、装置和计算机可读存储介质 |
WO2022116441A1 (zh) * | 2020-12-03 | 2022-06-09 | 平安科技(深圳)有限公司 | 基于卷积神经网络的bert模型的微调方法及装置 |
CN114692596A (zh) * | 2022-02-23 | 2022-07-01 | 北京快确信息科技有限公司 | 基于深度学习算法的债券信息解析方法、装置及电子设备 |
US20220230014A1 (en) * | 2021-01-19 | 2022-07-21 | Naver Corporation | Methods and systems for transfer learning of deep learning model based on document similarity learning |
CN115132181A (zh) * | 2022-04-26 | 2022-09-30 | 腾讯科技(深圳)有限公司 | 语音识别方法、装置、电子设备、存储介质及程序产品 |
CN115239638A (zh) * | 2022-06-28 | 2022-10-25 | 厦门微图软件科技有限公司 | 一种工业缺陷检测方法、装置、设备及可读存储介质 |
CN115564030A (zh) * | 2022-11-24 | 2023-01-03 | 中国平安财产保险股份有限公司 | 目标检测模型的压缩方法、检测方法、装置及相关设备 |
US20230020886A1 (en) * | 2021-07-08 | 2023-01-19 | Adobe Inc. | Auto-creation of custom models for text summarization |
CN116226334A (zh) * | 2023-03-03 | 2023-06-06 | 北京百度网讯科技有限公司 | 生成式大语言模型训练方法以及基于模型的搜索方法 |
WO2023113891A1 (en) * | 2021-12-17 | 2023-06-22 | Microsoft Technology Licensing, Llc. | Code generation through reinforcement learning using code-quality rewards |
CN116415170A (zh) * | 2023-03-20 | 2023-07-11 | 华南理工大学 | 基于预训练语言模型的提示学习小样本分类方法、系统、设备及介质 |
CN116415650A (zh) * | 2023-04-17 | 2023-07-11 | 惠州市沃羊文化发展有限公司 | 生成对话语言模型及生成对话的方法、装置和存储介质 |
CN116662552A (zh) * | 2023-06-29 | 2023-08-29 | 中国工商银行股份有限公司 | 金融文本数据分类方法、装置、终端设备及介质 |
CN116737927A (zh) * | 2023-06-09 | 2023-09-12 | 电子科技大学 | 一种用于序列标注的引力场约束模型蒸馏方法、系统、电子设备和存储介质 |
CN116775843A (zh) * | 2023-07-06 | 2023-09-19 | 平安科技(深圳)有限公司 | 问答对评测数据生成方法、装置、计算机设备及存储介质 |
-
2023
- 2023-09-27 CN CN202311259451.2A patent/CN117057413B/zh active Active
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109902371A (zh) * | 2019-02-19 | 2019-06-18 | 校宝在线(杭州)科技股份有限公司 | 一种基于深度强化学习的智能排课方法 |
CN112115724A (zh) * | 2020-07-23 | 2020-12-22 | 云知声智能科技股份有限公司 | 一种多领域神经网络在垂直领域微调的优化方法及系统 |
WO2022116441A1 (zh) * | 2020-12-03 | 2022-06-09 | 平安科技(深圳)有限公司 | 基于卷积神经网络的bert模型的微调方法及装置 |
US20220230014A1 (en) * | 2021-01-19 | 2022-07-21 | Naver Corporation | Methods and systems for transfer learning of deep learning model based on document similarity learning |
CN113076950A (zh) * | 2021-04-01 | 2021-07-06 | 安徽酷哇机器人有限公司 | 一种基于深度强化学习的图像数据自动化标注方法及系统 |
US20230020886A1 (en) * | 2021-07-08 | 2023-01-19 | Adobe Inc. | Auto-creation of custom models for text summarization |
CN113947196A (zh) * | 2021-10-25 | 2022-01-18 | 中兴通讯股份有限公司 | 网络模型训练方法、装置和计算机可读存储介质 |
WO2023113891A1 (en) * | 2021-12-17 | 2023-06-22 | Microsoft Technology Licensing, Llc. | Code generation through reinforcement learning using code-quality rewards |
CN114692596A (zh) * | 2022-02-23 | 2022-07-01 | 北京快确信息科技有限公司 | 基于深度学习算法的债券信息解析方法、装置及电子设备 |
CN115132181A (zh) * | 2022-04-26 | 2022-09-30 | 腾讯科技(深圳)有限公司 | 语音识别方法、装置、电子设备、存储介质及程序产品 |
CN115239638A (zh) * | 2022-06-28 | 2022-10-25 | 厦门微图软件科技有限公司 | 一种工业缺陷检测方法、装置、设备及可读存储介质 |
CN115564030A (zh) * | 2022-11-24 | 2023-01-03 | 中国平安财产保险股份有限公司 | 目标检测模型的压缩方法、检测方法、装置及相关设备 |
CN116226334A (zh) * | 2023-03-03 | 2023-06-06 | 北京百度网讯科技有限公司 | 生成式大语言模型训练方法以及基于模型的搜索方法 |
CN116415170A (zh) * | 2023-03-20 | 2023-07-11 | 华南理工大学 | 基于预训练语言模型的提示学习小样本分类方法、系统、设备及介质 |
CN116415650A (zh) * | 2023-04-17 | 2023-07-11 | 惠州市沃羊文化发展有限公司 | 生成对话语言模型及生成对话的方法、装置和存储介质 |
CN116737927A (zh) * | 2023-06-09 | 2023-09-12 | 电子科技大学 | 一种用于序列标注的引力场约束模型蒸馏方法、系统、电子设备和存储介质 |
CN116662552A (zh) * | 2023-06-29 | 2023-08-29 | 中国工商银行股份有限公司 | 金融文本数据分类方法、装置、终端设备及介质 |
CN116775843A (zh) * | 2023-07-06 | 2023-09-19 | 平安科技(深圳)有限公司 | 问答对评测数据生成方法、装置、计算机设备及存储介质 |
Non-Patent Citations (1)
Title |
---|
曾浩 等: "模型参数自适应的低复杂度ATPM-VSIMM算法", 《通信学报》, vol. 44, no. 9, pages 25 - 35 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117292119A (zh) * | 2023-11-24 | 2023-12-26 | 国网智能科技股份有限公司 | 一种输电多尺度目标检测方法及系统 |
CN117292119B (zh) * | 2023-11-24 | 2024-03-22 | 国网智能科技股份有限公司 | 一种输电多尺度目标检测方法及系统 |
Also Published As
Publication number | Publication date |
---|---|
CN117057413B (zh) | 2024-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110188331B (zh) | 模型训练方法、对话系统评价方法、装置、设备及存储介质 | |
CN110168578B (zh) | 具有任务特定路径的多任务神经网络 | |
US20220414464A1 (en) | Method and server for federated machine learning | |
US20230105590A1 (en) | Data classification and recognition method and apparatus, device, and medium | |
US11423311B2 (en) | Automatic tuning of artificial neural networks | |
US10354544B1 (en) | Predicting student proficiencies in knowledge components | |
EP3956821A1 (en) | Multi-task machine learning architectures and training procedures | |
CN111126574A (zh) | 基于内镜图像对机器学习模型进行训练的方法、装置和存储介质 | |
CN117057413B (zh) | 强化学习模型微调方法、装置、计算机设备及存储介质 | |
CN110210625B (zh) | 基于迁移学习的建模方法、装置、计算机设备和存储介质 | |
CN112465138A (zh) | 模型蒸馏方法、装置、存储介质及设备 | |
KR102084092B1 (ko) | 수학 교육 서비스 제공 방법, 학습 관리 서버 및 수학 교육 시스템 | |
CN114974397A (zh) | 蛋白质结构预测模型的训练方法和蛋白质结构预测方法 | |
EP4220555A1 (en) | Training method and apparatus for image segmentation model, image segmentation method and apparatus, and device | |
CN109086463A (zh) | 一种基于区域卷积神经网络的问答社区标签推荐方法 | |
CN114580517A (zh) | 一种图像识别模型的确定方法及装置 | |
WO2022072890A1 (en) | Neural architecture and hardware accelerator search | |
US20220027739A1 (en) | Search space exploration for deep learning | |
CN117216382A (zh) | 一种交互处理的方法、模型训练的方法以及相关装置 | |
CN111932160A (zh) | 知识掌握信息处理方法、装置、计算机设备及存储介质 | |
JP2021114097A (ja) | 画像判定システム | |
US20230419164A1 (en) | Multitask Machine-Learning Model Training and Training Data Augmentation | |
WO2022113175A1 (ja) | 処理方法、処理システム及び処理プログラム | |
CN114970732A (zh) | 分类模型的后验校准方法、装置、计算机设备及介质 | |
CN112102304A (zh) | 图像处理方法、装置、计算机设备和计算机可读存储介质 |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Country or region after: China Address after: 518000, 1005A, Tianlong Mobile Headquarters Building, Tongfa South Road, Xili Community, Xili Street, Nanshan District, Shenzhen, Guangdong Province Applicant after: Chuanshen Hongan Intelligent (Shenzhen) Co.,Ltd. Address before: 1301, Building F, Tongfang Information Port, No. 11, Langshan Road, Songpingshan Community, Xili Street, Nanshan District, Shenzhen, Guangdong 518000 Applicant before: Zhugao Intelligent Technology (Shenzhen) Co.,Ltd. Country or region before: China |
|
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240513 Address after: Room 305, Building 1, No. 455 Tangpu Road, Honghe Town, Xiuzhou District, Jiaxing City, Zhejiang Province, 314000 Patentee after: Chuanshen Intelligent Technology (Jiaxing) Co.,Ltd. Country or region after: China Address before: 518000, 1005A, Tianlong Mobile Headquarters Building, Tongfa South Road, Xili Community, Xili Street, Nanshan District, Shenzhen, Guangdong Province Patentee before: Chuanshen Hongan Intelligent (Shenzhen) Co.,Ltd. Country or region before: China |