CN110033091A - 一种基于模型进行预测的方法和装置 - Google Patents
一种基于模型进行预测的方法和装置 Download PDFInfo
- Publication number
- CN110033091A CN110033091A CN201811522364.0A CN201811522364A CN110033091A CN 110033091 A CN110033091 A CN 110033091A CN 201811522364 A CN201811522364 A CN 201811522364A CN 110033091 A CN110033091 A CN 110033091A
- Authority
- CN
- China
- Prior art keywords
- model
- running environment
- machine learning
- learning model
- request
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/048—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators using a predictor
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (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)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
索引 | 向量 |
0 | (1,2,3,4) |
1 | (5,6,7,8) |
2 | (9,10,11,12) |
3 | (13,14,15,16) |
4 | (17,18,19,20) |
Claims (11)
Priority Applications (6)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811522364.0A CN110033091B (zh) | 2018-12-13 | 2018-12-13 | 一种基于模型进行预测的方法和装置 |
TW108134608A TWI693563B (zh) | 2018-12-13 | 2019-09-25 | 基於模型進行預測的方法和裝置 |
EP19895453.9A EP3816877A4 (en) | 2018-12-13 | 2019-10-24 | MODEL-BASED PREDICTION METHOD AND DEVICE |
PCT/CN2019/112895 WO2020119268A1 (zh) | 2018-12-13 | 2019-10-24 | 一种基于模型进行预测的方法和装置 |
SG11202100954UA SG11202100954UA (en) | 2018-12-13 | 2019-10-24 | Model-based prediction method and apparatus |
US17/165,509 US11803752B2 (en) | 2018-12-13 | 2021-02-02 | Separate deployment of machine learning model and associated embedding |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811522364.0A CN110033091B (zh) | 2018-12-13 | 2018-12-13 | 一种基于模型进行预测的方法和装置 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110033091A true CN110033091A (zh) | 2019-07-19 |
CN110033091B CN110033091B (zh) | 2020-09-01 |
Family
ID=67235337
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811522364.0A Active CN110033091B (zh) | 2018-12-13 | 2018-12-13 | 一种基于模型进行预测的方法和装置 |
Country Status (6)
Country | Link |
---|---|
US (1) | US11803752B2 (zh) |
EP (1) | EP3816877A4 (zh) |
CN (1) | CN110033091B (zh) |
SG (1) | SG11202100954UA (zh) |
TW (1) | TWI693563B (zh) |
WO (1) | WO2020119268A1 (zh) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111158790A (zh) * | 2019-12-31 | 2020-05-15 | 清华大学 | 面向云端深度学习推理的fpga虚拟化方法 |
CN111178517A (zh) * | 2020-01-20 | 2020-05-19 | 上海依图网络科技有限公司 | 模型部署方法、系统、芯片、电子设备及介质 |
WO2020119268A1 (zh) * | 2018-12-13 | 2020-06-18 | 阿里巴巴集团控股有限公司 | 一种基于模型进行预测的方法和装置 |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102020211250A1 (de) * | 2020-09-08 | 2022-03-10 | Zf Friedrichshafen Ag | Computerimplementiertes Verfahren, eingebettetes System und Computerprogramm zum Ausführen einer Regelungs- und/oder Steuerungsvorschrift |
US20220165291A1 (en) * | 2020-11-20 | 2022-05-26 | Samsung Electronics Co., Ltd. | Electronic apparatus, control method thereof and electronic system |
CN115577760B (zh) * | 2021-07-14 | 2023-06-02 | 华为技术有限公司 | 一种数据处理方法、系统及相关设备 |
TWI818501B (zh) * | 2022-04-07 | 2023-10-11 | 創鑫智慧股份有限公司 | 嵌入表產生方法與嵌入表濃縮方法 |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040236806A1 (en) * | 2002-06-24 | 2004-11-25 | Turner James D. | Method, apparatus and articles of manufacture for computing the sensitivity partial derivatives of linked mechanical systems |
CN107330032A (zh) * | 2017-06-26 | 2017-11-07 | 北京理工大学 | 一种基于递归神经网络的隐式篇章关系分析方法 |
CN107423817A (zh) * | 2017-04-17 | 2017-12-01 | 星环信息科技(上海)有限公司 | 一种深度学习实现的方法及设备 |
CN107944027A (zh) * | 2017-12-12 | 2018-04-20 | 苏州思必驰信息科技有限公司 | 创建语义键索引的方法及系统 |
CN108153853A (zh) * | 2017-12-22 | 2018-06-12 | 齐鲁工业大学 | 基于Wikipedia链接结构的中文概念向量生成方法和装置 |
US20180197068A1 (en) * | 2016-10-27 | 2018-07-12 | Google Llc | Neural network instruction set architecture |
CN108492273A (zh) * | 2018-03-28 | 2018-09-04 | 深圳市唯特视科技有限公司 | 一种基于自注意力模型的图像生成方法 |
CN108805795A (zh) * | 2017-05-05 | 2018-11-13 | 英特尔公司 | 用于机器学习的硬件实现的点对点通信原语 |
CN108885571A (zh) * | 2016-04-05 | 2018-11-23 | 谷歌有限责任公司 | 分批处理机器学习模型的输入 |
Family Cites Families (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8837727B2 (en) * | 2011-11-08 | 2014-09-16 | Mitsubishi Electric Research Laboratories, Inc. | Method for privacy preserving hashing of signals with binary embeddings |
US9141916B1 (en) * | 2012-06-29 | 2015-09-22 | Google Inc. | Using embedding functions with a deep network |
US9147154B2 (en) * | 2013-03-13 | 2015-09-29 | Google Inc. | Classifying resources using a deep network |
EP3259688A4 (en) * | 2015-02-19 | 2018-12-12 | Digital Reasoning Systems, Inc. | Systems and methods for neural language modeling |
US9984062B1 (en) * | 2015-07-10 | 2018-05-29 | Google Llc | Generating author vectors |
US10395118B2 (en) * | 2015-10-29 | 2019-08-27 | Baidu Usa Llc | Systems and methods for video paragraph captioning using hierarchical recurrent neural networks |
US10664766B2 (en) * | 2016-01-27 | 2020-05-26 | Bonsai AI, Inc. | Graphical user interface to an artificial intelligence engine utilized to generate one or more trained artificial intelligence models |
CN109313719B (zh) * | 2016-03-18 | 2022-03-22 | 谷歌有限责任公司 | 使用神经网络生成文本段的依存性解析 |
KR102155261B1 (ko) * | 2016-04-13 | 2020-09-11 | 구글 엘엘씨 | 광역 및 심층 기계 학습 모델들 |
CN106127297B (zh) * | 2016-06-02 | 2019-07-12 | 中国科学院自动化研究所 | 基于张量分解的深度卷积神经网络的加速与压缩方法 |
US10055692B1 (en) * | 2017-02-21 | 2018-08-21 | Google Llc | Parallel processing of reduction and broadcast operations on large datasets of non-scalar data |
US10896367B2 (en) * | 2017-03-07 | 2021-01-19 | Google Llc | Depth concatenation using a matrix computation unit |
US10261786B2 (en) * | 2017-03-09 | 2019-04-16 | Google Llc | Vector processing unit |
US11640617B2 (en) * | 2017-03-21 | 2023-05-02 | Adobe Inc. | Metric forecasting employing a similarity determination in a digital medium environment |
US10943171B2 (en) * | 2017-09-01 | 2021-03-09 | Facebook, Inc. | Sparse neural network training optimization |
CN107563442B (zh) * | 2017-09-02 | 2019-12-10 | 西安电子科技大学 | 基于稀疏低秩正则图张量化嵌入的高光谱图像分类方法 |
CN110033091B (zh) * | 2018-12-13 | 2020-09-01 | 阿里巴巴集团控股有限公司 | 一种基于模型进行预测的方法和装置 |
-
2018
- 2018-12-13 CN CN201811522364.0A patent/CN110033091B/zh active Active
-
2019
- 2019-09-25 TW TW108134608A patent/TWI693563B/zh active
- 2019-10-24 WO PCT/CN2019/112895 patent/WO2020119268A1/zh unknown
- 2019-10-24 SG SG11202100954UA patent/SG11202100954UA/en unknown
- 2019-10-24 EP EP19895453.9A patent/EP3816877A4/en active Pending
-
2021
- 2021-02-02 US US17/165,509 patent/US11803752B2/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040236806A1 (en) * | 2002-06-24 | 2004-11-25 | Turner James D. | Method, apparatus and articles of manufacture for computing the sensitivity partial derivatives of linked mechanical systems |
CN108885571A (zh) * | 2016-04-05 | 2018-11-23 | 谷歌有限责任公司 | 分批处理机器学习模型的输入 |
US20180197068A1 (en) * | 2016-10-27 | 2018-07-12 | Google Llc | Neural network instruction set architecture |
CN107423817A (zh) * | 2017-04-17 | 2017-12-01 | 星环信息科技(上海)有限公司 | 一种深度学习实现的方法及设备 |
CN108805795A (zh) * | 2017-05-05 | 2018-11-13 | 英特尔公司 | 用于机器学习的硬件实现的点对点通信原语 |
CN107330032A (zh) * | 2017-06-26 | 2017-11-07 | 北京理工大学 | 一种基于递归神经网络的隐式篇章关系分析方法 |
CN107944027A (zh) * | 2017-12-12 | 2018-04-20 | 苏州思必驰信息科技有限公司 | 创建语义键索引的方法及系统 |
CN108153853A (zh) * | 2017-12-22 | 2018-06-12 | 齐鲁工业大学 | 基于Wikipedia链接结构的中文概念向量生成方法和装置 |
CN108492273A (zh) * | 2018-03-28 | 2018-09-04 | 深圳市唯特视科技有限公司 | 一种基于自注意力模型的图像生成方法 |
Non-Patent Citations (2)
Title |
---|
CHANG LIU,JILIU ZHOU,KUN HE等: "Supervised Locally Linear Embedding in Tensor Space", 《2009 THIRD INTERNATIONAL SYMPOSIUM ON INTELLIGENT INFORMATION TECHNOLOGY APPLICATION》 * |
章敏敏,徐和平,王晓洁等: "谷歌TensorFlow机器学习框架及应用", 《微型机与应用》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020119268A1 (zh) * | 2018-12-13 | 2020-06-18 | 阿里巴巴集团控股有限公司 | 一种基于模型进行预测的方法和装置 |
US11803752B2 (en) | 2018-12-13 | 2023-10-31 | Advanced New Technologies Co., Ltd. | Separate deployment of machine learning model and associated embedding |
CN111158790A (zh) * | 2019-12-31 | 2020-05-15 | 清华大学 | 面向云端深度学习推理的fpga虚拟化方法 |
CN111178517A (zh) * | 2020-01-20 | 2020-05-19 | 上海依图网络科技有限公司 | 模型部署方法、系统、芯片、电子设备及介质 |
CN111178517B (zh) * | 2020-01-20 | 2023-12-05 | 上海依图网络科技有限公司 | 模型部署方法、系统、芯片、电子设备及介质 |
Also Published As
Publication number | Publication date |
---|---|
WO2020119268A1 (zh) | 2020-06-18 |
TW202022719A (zh) | 2020-06-16 |
EP3816877A1 (en) | 2021-05-05 |
CN110033091B (zh) | 2020-09-01 |
US11803752B2 (en) | 2023-10-31 |
EP3816877A4 (en) | 2021-10-27 |
TWI693563B (zh) | 2020-05-11 |
SG11202100954UA (en) | 2021-02-25 |
US20210158165A1 (en) | 2021-05-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110033091A (zh) | 一种基于模型进行预测的方法和装置 | |
EP4036724A1 (en) | Method for splitting neural network model by using multi-core processor, and related product | |
US20190286972A1 (en) | Hardware accelerated neural network subgraphs | |
Karloff et al. | A model of computation for MapReduce | |
KR102319172B1 (ko) | 클라우드 컴퓨팅 기반의 플랫폼 제공 시스템 및 이를 이용한 플랫폼 제공 방법 | |
Galluppi et al. | A hierachical configuration system for a massively parallel neural hardware platform | |
JP2022046557A (ja) | 多目的の並列処理アーキテクチャ | |
Han et al. | Signal processing and networking for big data applications | |
Ma et al. | BaGuaLu: targeting brain scale pretrained models with over 37 million cores | |
Khezr et al. | MapReduce and its application in optimization algorithms: a comprehensive study | |
CN111860807B (zh) | 分形计算装置、方法、集成电路及板卡 | |
Blythe et al. | Farm: Architecture for distributed agent-based social simulations | |
Vidal et al. | Solving optimization problems using a hybrid systolic search on GPU plus CPU | |
KR102002732B1 (ko) | 앙상블 모델을 이용한 심층 신경망 기반 데이터 처리 방법 및 장치 | |
Tan et al. | A genetic programming hyper-heuristic approach for online resource allocation in container-based clouds | |
US11409564B2 (en) | Resource allocation for tuning hyperparameters of large-scale deep learning workloads | |
JP7220007B2 (ja) | 並列性及びオンチップ・メモリを介した時間、空間及びエネルギー効率のよいニューラル推論 | |
Plotnikova et al. | Gravitation search training algorithm for asynchronous distributed multilayer perceptron model | |
He et al. | Performance of Distributed Deep Learning Workloads on a Composable Cyberinfrastructure | |
Alshayeji et al. | Spark‐based parallel processing whale optimization algorithm | |
Jian et al. | Research on modeling and simulation of distributed supply chain based on HAS | |
Golubeva et al. | A tool for simulating parallel branch-and-bound methods | |
Chazapis et al. | EVOLVE: HPC and cloud enhanced testbed for extracting value from large-scale diverse data | |
Viviani | Deep Learning at Scale with Nearest Neighbours Communications | |
Lee et al. | An Optimal Network-Aware Scheduling Technique for Distributed Deep Learning in Distributed HPC Platforms. Electronics 2023, 12, 3021 |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20201013 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20201013 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Patentee before: Alibaba Group Holding Ltd. |
|
TR01 | Transfer of patent right |