JP2024509670A - 分割可能なディープニューラルネットワークにおける動的特徴サイズ適応 - Google Patents

分割可能なディープニューラルネットワークにおける動的特徴サイズ適応 Download PDF

Info

Publication number
JP2024509670A
JP2024509670A JP2023544040A JP2023544040A JP2024509670A JP 2024509670 A JP2024509670 A JP 2024509670A JP 2023544040 A JP2023544040 A JP 2023544040A JP 2023544040 A JP2023544040 A JP 2023544040A JP 2024509670 A JP2024509670 A JP 2024509670A
Authority
JP
Japan
Prior art keywords
neural network
dnn
compression
dnn model
compression factor
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
Application number
JP2023544040A
Other languages
English (en)
Japanese (ja)
Other versions
JP2024509670A5 (https=
Inventor
キルティ クマラスワミ、スレシュ
カン ンゴック ドゥオン、クアン
オゼロフ、アレクセイ
フォンテーヌ、パトリック
シュニッツラー、フランソワ
ランベール、アンヌ
ペレティエ、ギスラン
Original Assignee
インターディジタル・シーイー・パテント・ホールディングス・ソシエテ・パ・アクシオンス・シンプリフィエ
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 インターディジタル・シーイー・パテント・ホールディングス・ソシエテ・パ・アクシオンス・シンプリフィエ filed Critical インターディジタル・シーイー・パテント・ホールディングス・ソシエテ・パ・アクシオンス・シンプリフィエ
Publication of JP2024509670A publication Critical patent/JP2024509670A/ja
Publication of JP2024509670A5 publication Critical patent/JP2024509670A5/ja
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • 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
    • 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
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • 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
    • G06N3/09—Supervised learning
    • 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
    • G06N3/096—Transfer learning
    • 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
    • G06N3/098—Distributed learning, e.g. federated learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
    • H04L67/1004—Server selection for load balancing
    • H04L67/1008—Server selection for load balancing based on parameters of servers, e.g. available memory or workload
    • 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
    • H03—ELECTRONIC CIRCUITRY
    • H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
    • H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
    • H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
    • H03M7/60—General implementation details not specific to a particular type of compression
    • H03M7/6041—Compression optimized for errors
    • H—ELECTRICITY
    • H03—ELECTRONIC CIRCUITRY
    • H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
    • H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
    • H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
    • H03M7/60—General implementation details not specific to a particular type of compression
    • H03M7/6064—Selection of Compressor
    • H03M7/6076—Selection between compressors of the same type

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Computer Hardware Design (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)
JP2023544040A 2021-02-05 2022-02-03 分割可能なディープニューラルネットワークにおける動的特徴サイズ適応 Pending JP2024509670A (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
EP21305156 2021-02-05
EP21305156.8 2021-02-05
PCT/EP2022/052633 WO2022167547A1 (en) 2021-02-05 2022-02-03 Dynamic feature size adaptation in splitable deep neural networks

Publications (2)

Publication Number Publication Date
JP2024509670A true JP2024509670A (ja) 2024-03-05
JP2024509670A5 JP2024509670A5 (https=) 2025-02-12

Family

ID=74661327

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2023544040A Pending JP2024509670A (ja) 2021-02-05 2022-02-03 分割可能なディープニューラルネットワークにおける動的特徴サイズ適応

Country Status (5)

Country Link
US (1) US20240311621A1 (https=)
EP (1) EP4288907A1 (https=)
JP (1) JP2024509670A (https=)
CN (1) CN116940946A (https=)
WO (1) WO2022167547A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230422117A1 (en) * 2022-06-09 2023-12-28 Qualcomm Incorporated User equipment machine learning service continuity

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117632463A (zh) * 2022-08-24 2024-03-01 华为技术有限公司 一种计算任务的分割方法及相关装置
CN115499658B (zh) * 2022-09-20 2024-05-07 支付宝(杭州)信息技术有限公司 虚拟世界的数据传输方法及装置
CN118473556A (zh) * 2023-02-09 2024-08-09 索尼集团公司 用于分割学习的电子设备和方法、计算机可读存储介质
WO2024168748A1 (zh) * 2023-02-16 2024-08-22 富士通株式会社 模型发送和接收方法以及装置
US12526439B2 (en) 2023-04-22 2026-01-13 Qualcomm Incorporated Rate adaptation for video coding for machines
CN120958815A (zh) * 2023-04-22 2025-11-14 高通股份有限公司 用于机器的视频译码的速率自适应
CN121336391A (zh) * 2023-06-13 2026-01-13 华为技术有限公司 通信方法和通信装置
IL325805A (en) * 2023-07-18 2026-03-01 Interdigital Vc Holdings Inc Tensor information for intermediate data
WO2025019540A1 (en) * 2023-07-19 2025-01-23 Interdigital Vc Holdings, Inc. Multi-layer split points output information
WO2025047742A1 (ja) * 2023-08-30 2025-03-06 京セラ株式会社 通信制御方法及びユーザ装置
US12587970B2 (en) * 2023-09-05 2026-03-24 Qualcomm Incorporated Decibel compression point information reporting
EP4651458A1 (en) * 2024-05-13 2025-11-19 InterDigital CE Patent Holdings, SAS Methods, apparatuses and systems related to transport partial results data with intermediate data
CN118741441B (zh) * 2024-07-18 2025-02-28 北京物资学院 无线蜂窝网络中终端选择大语言模型的方法和装置
WO2026016173A1 (en) * 2024-07-19 2026-01-22 Apple Inc. Performance monitoring of chained ai model in wireless communications
CN118843159B (zh) * 2024-09-23 2024-11-19 四川科锐得电力通信技术有限公司 一种基于无线网桥的无信号区输电线路数据传输方法及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019191635A (ja) * 2018-04-18 2019-10-31 日本電信電話株式会社 データ分析システム、方法、及びプログラム
US20200372412A1 (en) * 2018-01-03 2020-11-26 Signify Holding B.V. System and methods to share machine learning functionality between cloud and an iot network
JPWO2019193660A1 (ja) * 2018-04-03 2021-04-22 株式会社ウフル 機械学習済みモデル切り替えシステム、エッジデバイス、機械学習済みモデル切り替え方法、及びプログラム

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102285064B1 (ko) * 2017-10-30 2021-08-04 한국전자통신연구원 은닉 변수를 이용하는 영상 및 신경망 압축을 위한 방법 및 장치
US11700518B2 (en) * 2019-05-31 2023-07-11 Huawei Technologies Co., Ltd. Methods and systems for relaying feature-driven communications

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200372412A1 (en) * 2018-01-03 2020-11-26 Signify Holding B.V. System and methods to share machine learning functionality between cloud and an iot network
JPWO2019193660A1 (ja) * 2018-04-03 2021-04-22 株式会社ウフル 機械学習済みモデル切り替えシステム、エッジデバイス、機械学習済みモデル切り替え方法、及びプログラム
JP2019191635A (ja) * 2018-04-18 2019-10-31 日本電信電話株式会社 データ分析システム、方法、及びプログラム

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
KO, JONG HWAN ほか: "Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained", ARXIV[ONLINE], JPN6026002792, 11 February 2018 (2018-02-11), ISSN: 0005787724 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20230422117A1 (en) * 2022-06-09 2023-12-28 Qualcomm Incorporated User equipment machine learning service continuity

Also Published As

Publication number Publication date
CN116940946A (zh) 2023-10-24
US20240311621A1 (en) 2024-09-19
WO2022167547A1 (en) 2022-08-11
EP4288907A1 (en) 2023-12-13

Similar Documents

Publication Publication Date Title
JP2024509670A (ja) 分割可能なディープニューラルネットワークにおける動的特徴サイズ適応
EP4122169B1 (en) Functional architecture and interface for non-real-time ran intelligent controller
US11509812B2 (en) Facilitation of collaborative camera field of view mapping
EP4022790A1 (en) Deep learning aided fingerprint based beam alignment
US20230292175A1 (en) Systems, apparatus, articles of manufacture, and methods for processing wireless data using baseband gateways
US11784883B2 (en) Automation agent for network equipment configuration
WO2014210441A1 (en) Method for selecting at least one parameter for downlink data transmission with a mobile user equipment
CN113225812B (zh) 一种确定波束信息的方法、终端及网络设备
US20240171241A1 (en) Joint beamforming weights and iq data scaling approach for improved fronthaul
US20210285788A1 (en) Shared overlay maps
US10778298B1 (en) Context-based precoding matrix computations for radio access network for 5G or other next generation network
WO2022172198A1 (en) Deep generative models for downlink channel estimation in fdd massive mimo systems
CN116615893B (zh) 下行链路mu-mimo传送中的码本和pmi覆写
CN111418162B (zh) 利用参考权重向量的ue特定的波束映射
EP4022795A1 (en) Apparatuses and methods for sequential receive combining
CN115865570B (zh) 通过信道状态信息报告增强多用户mimo的方法、基站
US11070971B2 (en) Self optimizing aggregation for 5G or other next generations wireless network
US20250071532A1 (en) Facilitation of local disaster mobile edge computing resiliency for 5g or other next generation network
US12074948B1 (en) Distributed and federated radio access network configuration management
US20220279615A1 (en) Session mapping in 5g and subsequent generation networks
US20220302993A1 (en) Cellular signal extension for private network device management
WO2025225851A1 (en) Method and apparatus for a large channel model in a wireless communication system
US20210029557A1 (en) Radio frequency database automation for 5g or other next generation network
US20250056211A1 (en) Capability information transmission
US20220361066A1 (en) Inference based neighbor relation configuration

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20230925

RD02 Notification of acceptance of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7422

Effective date: 20231016

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20250203

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20250203

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20251211

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20260203

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20260408