CN115917560A - 信息处理装置、信息处理方法以及信息处理程序 - Google Patents

信息处理装置、信息处理方法以及信息处理程序 Download PDF

Info

Publication number
CN115917560A
CN115917560A CN202080102834.7A CN202080102834A CN115917560A CN 115917560 A CN115917560 A CN 115917560A CN 202080102834 A CN202080102834 A CN 202080102834A CN 115917560 A CN115917560 A CN 115917560A
Authority
CN
China
Prior art keywords
quantization
information processing
processor
gradient
neural network
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
CN202080102834.7A
Other languages
English (en)
Chinese (zh)
Inventor
坂井靖文
恩谢·克雷什帕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujitsu Ltd
Original Assignee
Fujitsu Ltd
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 Fujitsu Ltd filed Critical Fujitsu Ltd
Publication of CN115917560A publication Critical patent/CN115917560A/zh
Pending legal-status Critical Current

Links

Images

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
    • G06N3/08—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
    • G06N3/08—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
    • G06N20/00—Machine 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
    • G06N3/04—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
    • G06N3/0464—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
    • G06N3/048—Activation functions
    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • 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
    • G06N3/08—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
    • G06N3/09—Supervised learning

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)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Neurology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
CN202080102834.7A 2020-07-10 2020-12-22 信息处理装置、信息处理方法以及信息处理程序 Pending CN115917560A (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
PCT/JP2020/027134 WO2022009433A1 (ja) 2020-07-10 2020-07-10 情報処理装置,情報処理方法および情報処理プログラム
JPPCT/JP2020/027134 2020-07-10
PCT/JP2020/047958 WO2022009449A1 (ja) 2020-07-10 2020-12-22 情報処理装置,情報処理方法および情報処理プログラム

Publications (1)

Publication Number Publication Date
CN115917560A true CN115917560A (zh) 2023-04-04

Family

ID=79553188

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080102834.7A Pending CN115917560A (zh) 2020-07-10 2020-12-22 信息处理装置、信息处理方法以及信息处理程序

Country Status (5)

Country Link
US (1) US20230123756A1 (cg-RX-API-DMAC7.html)
EP (1) EP4181022A1 (cg-RX-API-DMAC7.html)
JP (1) JPWO2022009449A1 (cg-RX-API-DMAC7.html)
CN (1) CN115917560A (cg-RX-API-DMAC7.html)
WO (2) WO2022009433A1 (cg-RX-API-DMAC7.html)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240070518A1 (en) * 2022-08-26 2024-02-29 Dell Products L.P. Smart communication in federated learning for transient and resource-constrained mobile edge devices
CN116187387B (zh) * 2023-02-22 2026-04-10 伟光有限公司 神经网络模型量化方法、装置、计算机设备和存储介质
JP2025096942A (ja) * 2023-12-18 2025-06-30 マクセル株式会社 学習方法及び学習装置
US20250265239A1 (en) * 2024-02-21 2025-08-21 Macronix International Co., Ltd. Quantization Error Compensation for Vector Computing

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0784975A (ja) * 1993-09-10 1995-03-31 Hitachi Ltd 情報処理装置および学習演算処理方法
CN108345939B (zh) * 2017-01-25 2022-05-24 微软技术许可有限责任公司 基于定点运算的神经网络
JP6823495B2 (ja) * 2017-02-27 2021-02-03 株式会社日立製作所 情報処理装置および画像認識装置
KR102526818B1 (ko) 2017-07-07 2023-04-27 미쓰비시덴키 가부시키가이샤 데이터 처리 장치, 데이터 처리 방법 및 기억 매체
KR102601604B1 (ko) * 2017-08-04 2023-11-13 삼성전자주식회사 뉴럴 네트워크의 파라미터들을 양자화하는 방법 및 장치
KR102564456B1 (ko) * 2017-10-19 2023-08-07 삼성전자주식회사 뉴럴 네트워크의 파라미터를 양자화하는 장치 및 방법
JP2019080232A (ja) * 2017-10-26 2019-05-23 株式会社Preferred Networks 勾配圧縮装置、勾配圧縮方法及びプログラム
GB2568084B (en) * 2017-11-03 2022-01-12 Imagination Tech Ltd Error allocation format selection for hardware implementation of deep neural network

Also Published As

Publication number Publication date
JPWO2022009449A1 (cg-RX-API-DMAC7.html) 2022-01-13
EP4181022A1 (en) 2023-05-17
WO2022009433A1 (ja) 2022-01-13
US20230123756A1 (en) 2023-04-20
WO2022009449A1 (ja) 2022-01-13

Similar Documents

Publication Publication Date Title
US20230123756A1 (en) Tensor quantization apparatus, tensor quantization method, and storage medium
US11043962B2 (en) Information processing apparatus, information processing method, and recording medium
US20190050734A1 (en) Compression method of deep neural networks
CN111340227A (zh) 通过强化学习模型对业务预测模型进行压缩的方法和装置
JP2017097585A (ja) 学習装置、プログラム及び学習方法
KR20220032861A (ko) 하드웨어에서의 성능을 고려한 뉴럴 아키텍처 서치 방법 빛 장치
CN112508167A (zh) 信息处理装置和方法以及记录介质
CN118410851A (zh) 一种混合专家模型路由网络优化方法、产品、装置及介质
KR102409476B1 (ko) 인공 신경망을 위한 양자화기 및 이의 손실 역전파 방법
US20200356850A1 (en) Fusion of neural networks
JP7047283B2 (ja) 情報処理装置、方法、及びプログラム
JP7436830B2 (ja) 学習プログラム、学習方法、および学習装置
KR20210138382A (ko) 뉴럴 네트워크에서의 다중 레벨 단계적 양자화 방법 및 장치
CN118230809A (zh) 基因因果关系预测方法、装置及电子设备
US12423555B2 (en) Storage medium storing quantization program, quantization method, and quantization apparatus
JP2019211985A (ja) 学習プログラム、学習方法、及び情報処理装置
CN113095328B (zh) 一种基尼指数引导的基于自训练的语义分割方法
JP7438544B2 (ja) ニューラルネットワーク処理装置、コンピュータプログラム、ニューラルネットワーク製造方法、ニューラルネットワークデータの製造方法、ニューラルネットワーク利用装置、及びニューラルネットワーク小規模化方法
US12614383B2 (en) Learning apparatus and learning method
JP2022054660A (ja) ニューラルネットワーク軽量化装置、ニューラルネットワーク軽量化方法およびプログラム
WO2025186881A1 (ja) 情報処理装置、情報処理方法、及び記録媒体
KR102962371B1 (ko) 신경망 네트워크 분리와 결합을 이용한 학습 방법 및 그 장치
JP2021044783A (ja) 情報処理装置,情報処理方法および情報処理プログラム
CN118839736A (zh) 一种深度神经网络的自适应量化方法、系统及产品
WO2025249066A1 (ja) 学習装置、制御装置、学習方法および記録媒体

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20230404