TW202239152A - 用於神經網路架構的編碼技術 - Google Patents

用於神經網路架構的編碼技術 Download PDF

Info

Publication number
TW202239152A
TW202239152A TW111104256A TW111104256A TW202239152A TW 202239152 A TW202239152 A TW 202239152A TW 111104256 A TW111104256 A TW 111104256A TW 111104256 A TW111104256 A TW 111104256A TW 202239152 A TW202239152 A TW 202239152A
Authority
TW
Taiwan
Prior art keywords
encoding
compressed data
data set
encoded
quantized
Prior art date
Application number
TW111104256A
Other languages
English (en)
Chinese (zh)
Inventor
帕樊庫馬爾 維泰拉德芙尼
泰尚 柳
納嘉 布桑
南宮俊
Original Assignee
美商高通公司
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 美商高通公司 filed Critical 美商高通公司
Publication of TW202239152A publication Critical patent/TW202239152A/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
    • 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
    • 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
    • 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
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder 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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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
    • G06N3/0495—Quantised networks; Sparse networks; Compressed networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G06T9/002—Image coding using neural networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/04—Protocols for data compression, e.g. ROHC
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/20—Control channels or signalling for resource management
    • H04W72/23—Control channels or signalling for resource management in the downlink direction of a wireless link, i.e. towards a terminal
    • 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
    • G06N3/048—Activation functions
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Multimedia (AREA)
  • Computer Security & Cryptography (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Mobile Radio Communication Systems (AREA)
TW111104256A 2021-03-05 2022-02-07 用於神經網路架構的編碼技術 TW202239152A (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/194,077 US12361277B2 (en) 2021-03-05 2021-03-05 Encoding techniques for neural network architectures
US17/194,077 2021-03-05

Publications (1)

Publication Number Publication Date
TW202239152A true TW202239152A (zh) 2022-10-01

Family

ID=80445982

Family Applications (1)

Application Number Title Priority Date Filing Date
TW111104256A TW202239152A (zh) 2021-03-05 2022-02-07 用於神經網路架構的編碼技術

Country Status (8)

Country Link
US (1) US12361277B2 (https=)
EP (1) EP4302232A1 (https=)
JP (1) JP2024509502A (https=)
KR (1) KR20230154014A (https=)
CN (1) CN116917902A (https=)
BR (1) BR112023017266A2 (https=)
TW (1) TW202239152A (https=)
WO (1) WO2022186947A1 (https=)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022040661A1 (en) * 2020-08-18 2022-02-24 Qualcomm Incorporated Reporting weight updates to a neural network for generating channel state information feedback
FI20206314A1 (en) * 2020-12-16 2022-06-17 Nokia Technologies Oy ESTIMATION OF DELAY SPREAD AND DOPPLER SPREAD
EP4304095A1 (en) * 2022-07-05 2024-01-10 The Boeing Company Compression and distribution of meteorological data using machine learning
WO2024065296A1 (zh) * 2022-09-28 2024-04-04 华为技术有限公司 数据传输方法及装置
CN116155453B (zh) * 2023-04-23 2023-07-07 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) 一种面向动态信噪比的译码方法及相关设备
WO2025091206A1 (en) * 2023-10-31 2025-05-08 Qualcomm Incorporated Configuration of entropy coding for channel state feedback
CN120201092A (zh) * 2023-12-21 2025-06-24 华为技术有限公司 数据压缩的方法和装置

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6919825B2 (en) * 2003-09-25 2005-07-19 Peerless Systems Corporation Split runlength encoding method and apparatus
EP3564864A4 (en) 2016-12-30 2020-04-15 Shanghai Cambricon Information Technology Co., Ltd DEVICES FOR COMPRESSION / DECOMPRESSION, SYSTEM, CHIP AND ELECTRONIC DEVICE
CN117676138A (zh) * 2017-12-06 2024-03-08 V-诺瓦国际有限公司 编码信号的方法、编码器、解码数据流的方法以及解码器
US11257254B2 (en) 2018-07-20 2022-02-22 Google Llc Data compression using conditional entropy models
WO2020068498A1 (en) 2018-09-27 2020-04-02 Google Llc Data compression using integer neural networks

Also Published As

Publication number Publication date
US20220284282A1 (en) 2022-09-08
JP2024509502A (ja) 2024-03-04
BR112023017266A2 (pt) 2023-09-26
KR20230154014A (ko) 2023-11-07
CN116917902A (zh) 2023-10-20
WO2022186947A1 (en) 2022-09-09
EP4302232A1 (en) 2024-01-10
US12361277B2 (en) 2025-07-15

Similar Documents

Publication Publication Date Title
CN115136520B (zh) 使用编码器神经网络的经压缩的测量反馈
CN116057898B (zh) 用于信道状态信息方案的神经网络或层配置指示符
US12445872B2 (en) Online training and augmentation of neural networks for channel state feedback
TW202239152A (zh) 用於神經網路架構的編碼技術
TWI821498B (zh) 針對通道狀態資訊的係數指示
CN117223230A (zh) 用于信道状态信息和信道压缩切换的技术
CN115053474B (zh) 下行链路控制信息中的外部编码方案
US20230316062A1 (en) Layer-by-layer training for federated learning
US12255714B2 (en) Techniques for encoding and decoding a channel between wireless communication devices
US12052126B2 (en) Modulating reference signals for conveying feedback information
CN121794978A (zh) 物理级图像压缩和发送
CN116134917A (zh) 用于适配在侧行链路通信系统中的资源感测的技术
CN115836498B (zh) 用于广播中的网络译码终止的反馈设计
CN118575425A (zh) 用于预译码矩阵指示符报告的技术
WO2023097551A1 (en) Machine learning models for precoding
CN118633255A (zh) 具有外部译码的灵活反馈
US12355537B2 (en) Feedback codebooks with bundling
US20250139737A1 (en) Signaling of sensor specific raw image mask
CN119013931A (zh) 侧链路中的冗余版本选择
CN115868127A (zh) 使用具有反馈的网络编码来广播分组
CN119769049A (zh) 用于基于设备存储装置的网络译码的技术