KR20230005868A - 신경망의 가중치 파라미터들을 디코딩하기 위한 디코더, 인코더, 방법들 및 확률 추정 파라미터들을 사용하는 인코딩된 표현 - Google Patents

신경망의 가중치 파라미터들을 디코딩하기 위한 디코더, 인코더, 방법들 및 확률 추정 파라미터들을 사용하는 인코딩된 표현 Download PDF

Info

Publication number
KR20230005868A
KR20230005868A KR1020227039550A KR20227039550A KR20230005868A KR 20230005868 A KR20230005868 A KR 20230005868A KR 1020227039550 A KR1020227039550 A KR 1020227039550A KR 20227039550 A KR20227039550 A KR 20227039550A KR 20230005868 A KR20230005868 A KR 20230005868A
Authority
KR
South Korea
Prior art keywords
parameters
neural network
parameter values
probability estimation
usable
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
KR1020227039550A
Other languages
English (en)
Korean (ko)
Inventor
폴 핫세
카르스튼 뮐러
하이너 키르히호퍼
하이코 슈봐르츠
디플레프 마르프
토마스 뷔간트
Original Assignee
프라운호퍼-게젤샤프트 추르 푀르데룽 데어 안제반텐 포르슝 에 파우
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 프라운호퍼-게젤샤프트 추르 푀르데룽 데어 안제반텐 포르슝 에 파우 filed Critical 프라운호퍼-게젤샤프트 추르 푀르데룽 데어 안제반텐 포르슝 에 파우
Publication of KR20230005868A publication Critical patent/KR20230005868A/ko
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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • 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
    • H03M7/70—Type of the data to be coded, other than image and sound
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/211—Selection of the most significant subset of features
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
    • 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
    • G06N3/047—Probabilistic or stochastic 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
    • G06N3/0499—Feedforward 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
    • 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
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
    • 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
    • H03M7/40—Conversion to or from variable length codes, e.g. Shannon-Fano code, Huffman code, Morse code
    • H03M7/4006—Conversion to or from arithmetic code
    • H03M7/4012—Binary arithmetic codes
    • H03M7/4018—Context adapative binary arithmetic codes [CABAC]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Neurology (AREA)
  • Algebra (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
KR1020227039550A 2020-04-14 2021-04-13 신경망의 가중치 파라미터들을 디코딩하기 위한 디코더, 인코더, 방법들 및 확률 추정 파라미터들을 사용하는 인코딩된 표현 Pending KR20230005868A (ko)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
EP20169498 2020-04-14
EP20169498.1 2020-04-14
PCT/EP2021/059594 WO2021209470A1 (en) 2020-04-14 2021-04-13 Decoder for decoding weight parameters of a neural network, encoder, methods and encoded representation using probability estimation parameters

Publications (1)

Publication Number Publication Date
KR20230005868A true KR20230005868A (ko) 2023-01-10

Family

ID=70390747

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020227039550A Pending KR20230005868A (ko) 2020-04-14 2021-04-13 신경망의 가중치 파라미터들을 디코딩하기 위한 디코더, 인코더, 방법들 및 확률 추정 파라미터들을 사용하는 인코딩된 표현

Country Status (6)

Country Link
US (1) US20230141029A1 (https=)
EP (1) EP4136756A1 (https=)
JP (2) JP7695954B2 (https=)
KR (1) KR20230005868A (https=)
CN (1) CN115699585A (https=)
WO (1) WO2021209470A1 (https=)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115699020A (zh) * 2020-06-05 2023-02-03 华为技术有限公司 用于神经网络的量化
US20230050279A1 (en) * 2021-08-12 2023-02-16 Taiwan Semiconductor Manufacturing Company, Ltd. Integrated circuit and method of operating same
CN121488473A (zh) * 2023-06-30 2026-02-06 抖音视界有限公司 用于可视数据处理的方法、装置和介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9088796B2 (en) * 2011-11-07 2015-07-21 Sharp Kabushiki Kaisha Video decoder with enhanced CABAC decoding
JP6159240B2 (ja) * 2013-12-09 2017-07-05 日本電信電話株式会社 二値算術符号化装置、二値算術符号化方法及び二値算術符号化プログラム
US10225555B2 (en) * 2015-05-19 2019-03-05 Mediatek Inc. Method and apparatus for multi-table based context adaptive binary arithmetic coding
CN107736027B (zh) * 2015-06-12 2021-06-01 松下知识产权经营株式会社 图像编码方法、图像解码方法、图像编码装置及图像解码装置
EP3562162A1 (en) * 2018-04-27 2019-10-30 InterDigital VC Holdings, Inc. Method and apparatus for video encoding and decoding based on neural network implementation of cabac
CN112689960B (zh) * 2018-07-06 2025-10-17 弗劳恩霍夫应用研究促进协会 算术编码器、算术解码器、视频编码器、视频解码器、编码方法、解码方法和计算机程序
JP2020022145A (ja) * 2018-08-03 2020-02-06 日本放送協会 符号化装置、復号装置、学習装置及びプログラム

Also Published As

Publication number Publication date
JP2023522887A (ja) 2023-06-01
EP4136756A1 (en) 2023-02-22
JP2025081713A (ja) 2025-05-27
JP7695954B2 (ja) 2025-06-19
WO2021209470A1 (en) 2021-10-21
US20230141029A1 (en) 2023-05-11
JP7817477B2 (ja) 2026-02-18
CN115699585A (zh) 2023-02-03

Similar Documents

Publication Publication Date Title
JP7817477B2 (ja) ニューラルネットワークの重みパラメーターを復号化するデコーダー、エンコーダー、方法、及び確率推定パラメーターを使用する符号化表現
JP6814780B2 (ja) 動きベクトル差のエントロピー符号化
TWI744827B (zh) 用以壓縮類神經網路參數之方法與裝置
US20250343764A1 (en) Concepts for Coding Neural Networks Parameters
JP5736032B2 (ja) 算術符号化のための適応型２値化
KR102617187B1 (ko) 비디오 디코더, 비디오 인코더, 비디오 컨텐츠를 디코딩하기 위한 방법, 비디오 컨텐츠를 인코딩하기 위한 방법, 컴퓨터 프로그램 및 비디오 비트스트림
TWI827010B (zh) 算術編碼器、算術解碼器、視訊編碼器、視訊解碼器、編碼方法、解碼方法及電腦程式
KR20230010854A (ko) 뉴럴 네트워크 파라미터들의 표현에 대한 향상된 개념
CN114731407B (zh) 算术编码器和解码器、视频编码器和解码器、用于编码或解码符号的方法以及用于编码或解码视频内容的方法
JP2025186542A (ja) 更新モデルを使用して、ニューラルネットワークパラメーターを復号化する装置、方法及びコンピュータープログラム、並びにニューラルネットワークパラメーターを符号化する装置、方法及びコンピュータープログラム
US20120218131A1 (en) Methods for arithmetic coding and decoding
US20240364362A1 (en) Concepts for encoding and decoding neural network parameters
WO2016025281A1 (en) Method for coding pulse vectors using statistical properties
Benierbah et al. Symbol positions‐based Slepian–Wolf coding with application to distributed video coding
JP2026071331A (ja) ニューラルネットワークの重みパラメーターを復号化するデコーダー、エンコーダー、方法、及び確率推定パラメーターを使用する符号化表現
TW202606302A (zh) 算術編碼器、算術解碼器、視訊編碼器、視訊解碼器、編碼方法、解碼方法和電腦程式
Tuan et al. Index Assignment Optimization for Digital Communication Systems Using M-ary Modulation Schemes
WO2006134521A1 (en) Adaptive encoding and decoding of a stream of signal values

Legal Events

Date Code Title Description
P11-X000 Amendment of application requested

St.27 status event code: A-2-2-P10-P11-nap-X000

P13-X000 Application amended

St.27 status event code: A-2-2-P10-P13-nap-X000

PA0105 International application

St.27 status event code: A-0-1-A10-A15-nap-PA0105

PA0201 Request for examination

St.27 status event code: A-1-2-D10-D11-exm-PA0201

P11-X000 Amendment of application requested

St.27 status event code: A-2-2-P10-P11-nap-X000

P13-X000 Application amended

St.27 status event code: A-2-2-P10-P13-nap-X000

PG1501 Laying open of application

St.27 status event code: A-1-1-Q10-Q12-nap-PG1501

P22-X000 Classification modified

St.27 status event code: A-2-2-P10-P22-nap-X000

D21 Rejection of application intended

Free format text: ST27 STATUS EVENT CODE: A-1-2-D10-D21-EXM-PE0902 (AS PROVIDED BY THE NATIONAL OFFICE)

PE0902 Notice of grounds for rejection

St.27 status event code: A-1-2-D10-D21-exm-PE0902