CN115280335A - 一种机器学习模型训练方法、电子设备及存储介质 - Google Patents
一种机器学习模型训练方法、电子设备及存储介质 Download PDFInfo
- Publication number
- CN115280335A CN115280335A CN202080098536.5A CN202080098536A CN115280335A CN 115280335 A CN115280335 A CN 115280335A CN 202080098536 A CN202080098536 A CN 202080098536A CN 115280335 A CN115280335 A CN 115280335A
- Authority
- CN
- China
- Prior art keywords
- node
- quantization
- strategy
- quantization strategy
- indication information
- 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
Links
Images
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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder 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
- G06N3/08—Learning methods
-
- 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
- G06N3/0495—Quantised networks; Sparse networks; Compressed 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
- G06N3/08—Learning methods
- G06N3/098—Distributed learning, e.g. federated learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0023—Systems modifying transmission characteristics according to link quality, e.g. power backoff characterised by the signalling
- H04L1/0026—Transmission of channel quality indication
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (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)
- Quality & Reliability (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
本申请公开了一种机器学习模型训练方法，包括：第一节点发送第一指示信息，所述第一指示信息用于第二节点确定第一量化策略，所述第一量化策略用于确定机器学习模型的参数和/或输出结果。本申请还公开了另一种机器学习模型训练方法、电子设备及存储介质。
Description
PCT国内申请，说明书已公开。
Claims (52)
- PCT国内申请，权利要求书已公开。
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2020/080787 WO2021189225A1 (zh) | 2020-03-24 | 2020-03-24 | 一种机器学习模型训练方法、电子设备及存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115280335A true CN115280335A (zh) | 2022-11-01 |
Family
ID=77890130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202080098536.5A Pending CN115280335A (zh) | 2020-03-24 | 2020-03-24 | 一种机器学习模型训练方法、电子设备及存储介质 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20230012043A1 (zh) |
| EP (1) | EP4131088A4 (zh) |
| CN (1) | CN115280335A (zh) |
| WO (1) | WO2021189225A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024099131A1 (zh) * | 2022-11-11 | 2024-05-16 | 华为技术有限公司 | 一种机器学习的管控方法和装置 |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116010072A (zh) * | 2021-10-22 | 2023-04-25 | 华为技术有限公司 | 机器学习模型的训练方法和装置 |
| CN116579438A (zh) * | 2022-01-29 | 2023-08-11 | 华为技术有限公司 | 信息处理方法及装置 |
| CN114584436B (zh) * | 2022-05-06 | 2022-07-01 | 北京理工大学 | 一种单次握手的并发通信网络中的消息聚合系统及方法 |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11068780B2 (en) * | 2017-04-01 | 2021-07-20 | Intel Corporation | Technologies for scaling deep learning training |
| US10833897B2 (en) * | 2017-05-04 | 2020-11-10 | At&T Intellectual Property I, L.P. | Employing modulation layer mapping to improve performance of MIMO communication systems |
| WO2019009897A1 (en) * | 2017-07-06 | 2019-01-10 | Google Llc | SYSTEMS AND METHODS FOR COMPRESSION AND DISTRIBUTION OF MACHINE LEARNING MODELS |
| US10721471B2 (en) * | 2017-10-26 | 2020-07-21 | Intel Corporation | Deep learning based quantization parameter estimation for video encoding |
| JP7045947B2 (ja) * | 2018-07-05 | 2022-04-01 | 株式会社日立製作所 | ニューラルネットワークの学習装置および学習方法 |
| US10902287B2 (en) * | 2018-09-17 | 2021-01-26 | At&T Intellectual Property I, L.P. | Data harvesting for machine learning model training |
| CN110659678B (zh) * | 2019-09-09 | 2023-11-17 | 腾讯科技（深圳）有限公司 | 一种用户行为分类方法、系统及存储介质 |
-
2020
- 2020-03-24 WO PCT/CN2020/080787 patent/WO2021189225A1/zh unknown
- 2020-03-24 EP EP20926427.4A patent/EP4131088A4/en active Pending
- 2020-03-24 CN CN202080098536.5A patent/CN115280335A/zh active Pending
-
2022
- 2022-09-22 US US17/934,573 patent/US20230012043A1/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024099131A1 (zh) * | 2022-11-11 | 2024-05-16 | 华为技术有限公司 | 一种机器学习的管控方法和装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| US20230012043A1 (en) | 2023-01-12 |
| EP4131088A1 (en) | 2023-02-08 |
| EP4131088A4 (en) | 2023-05-10 |
| WO2021189225A1 (zh) | 2021-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115280335A (zh) | 一种机器学习模型训练方法、电子设备及存储介质 | |
| CN115280338A (zh) | 一种基于联邦学习的模型训练方法、电子设备及存储介质 | |
| EP3979533A1 (en) | Channel state information processing method, electronic device, and storage medium | |
| WO2021237423A1 (zh) | 一种信道状态信息传输方法、电子设备及存储介质 | |
| WO2021237715A1 (zh) | 一种信道状态信息处理方法、电子设备及存储介质 | |
| CN114270723A (zh) | 一种信道状态信息处理方法、电子设备及存储介质 | |
| EP4277398A1 (en) | Mode indication method, terminal device, and network device | |
| US11425663B2 (en) | Wireless communication method, terminal device, and network device | |
| CN113711660A (zh) | 无线通信的方法、终端设备和网络设备 | |
| US20230276502A1 (en) | Random access method, communication device and storage medium | |
| CN110838861B (zh) | 信号传输方法、波束确定方法及其装置 | |
| EP4383866A1 (en) | Paging processing method and apparatus | |
| US12127235B2 (en) | Method for processing CSI, terminal device, and network device | |
| US20230007529A1 (en) | Data transmission method, electronic device, and storage medium | |
| CN114585107B (zh) | 终端rrc连接恢复的方法和装置 | |
| WO2022021371A1 (zh) | 一种会话建立方法、电子设备及存储介质 | |
| US20230353300A1 (en) | Information sending method, information receiving method, apparatus, device, and medium | |
| CN118301790A (zh) | Ue标识方法、装置及存储介质 | |
| CN117500042A (zh) | 定位处理方法、装置及设备 | |
| CN118524439A (zh) | 一种信息传输方法、装置及设备 | |
| CN117202338A (zh) | 定时提前值传输方法、装置及存储介质 | |
| CN117835167A (zh) | 业务数据的接收方法、装置、第一终端和网络设备 | |
| CN116962991A (zh) | 信息传输方法、终端、网络设备、装置及存储介质 | |
| CN118678368A (zh) | 一种信息处理方法、终端设备和网络设备 | |
| CN118158732A (zh) | 非周期cli汇报方法及装置、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 |