KR20230073757A - 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 - Google Patents

심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 Download PDF

Info

Publication number
KR20230073757A
KR20230073757A KR1020210160472A KR20210160472A KR20230073757A KR 20230073757 A KR20230073757 A KR 20230073757A KR 1020210160472 A KR1020210160472 A KR 1020210160472A KR 20210160472 A KR20210160472 A KR 20210160472A KR 20230073757 A KR20230073757 A KR 20230073757A
Authority
KR
South Korea
Prior art keywords
pruning
trunk
layer
kernels
kernel
Prior art date
Application number
KR1020210160472A
Other languages
English (en)
Korean (ko)
Inventor
김현
김남준
Original Assignee
서울과학기술대학교 산학협력단
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 서울과학기술대학교 산학협력단 filed Critical 서울과학기술대학교 산학협력단
Priority to KR1020210160472A priority Critical patent/KR20230073757A/ko
Priority to PCT/KR2021/017227 priority patent/WO2023090499A1/fr
Publication of KR20230073757A publication Critical patent/KR20230073757A/ko

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
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • 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
    • 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
    • G06N3/08—Learning methods
    • G06N3/088—Non-supervised learning, e.g. competitive learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Filters That Use Time-Delay Elements (AREA)
KR1020210160472A 2021-11-19 2021-11-19 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 KR20230073757A (ko)

Priority Applications (2)

Application Number Priority Date Filing Date Title
KR1020210160472A KR20230073757A (ko) 2021-11-19 2021-11-19 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법
PCT/KR2021/017227 WO2023090499A1 (fr) 2021-11-19 2021-11-23 Procédé d'élagage de filtre basé sur l'apprentissage de la rareté pour réseaux neuronaux profonds

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020210160472A KR20230073757A (ko) 2021-11-19 2021-11-19 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법

Publications (1)

Publication Number Publication Date
KR20230073757A true KR20230073757A (ko) 2023-05-26

Family

ID=86397142

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020210160472A KR20230073757A (ko) 2021-11-19 2021-11-19 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법

Country Status (2)

Country Link
KR (1) KR20230073757A (fr)
WO (1) WO2023090499A1 (fr)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10482337B2 (en) * 2017-09-29 2019-11-19 Infineon Technologies Ag Accelerating convolutional neural network computation throughput
KR102225308B1 (ko) * 2017-11-28 2021-03-09 주식회사 날비컴퍼니 컨볼루션 신경망 내 필터 프루닝 장치 및 방법
KR102165273B1 (ko) * 2019-04-02 2020-10-13 국방과학연구소 소형 뉴럴 네트워크의 채널 프루닝(pruning) 방법 및 시스템
KR20210012882A (ko) * 2019-07-25 2021-02-03 삼성전자주식회사 컨볼루션 뉴럴 네트워크의 성능 향상을 위한 방법 및 시스템

Also Published As

Publication number Publication date
WO2023090499A1 (fr) 2023-05-25

Similar Documents

Publication Publication Date Title
US11741342B2 (en) Resource-efficient neural architects
CN109726045B (zh) 用于块稀疏递归神经网络的系统和方法
Tung et al. Deep neural network compression by in-parallel pruning-quantization
CN112508169A (zh) 知识蒸馏方法和系统
EP4372616A1 (fr) Système et procédé pour réseaux d'autoroute récurrentes normalisés par lots
CN111709493B (zh) 对象分类方法、训练方法、装置、设备及存储介质
US11544526B2 (en) Computing device and method
CN110782008A (zh) 深度学习模型的训练方法、预测方法和装置
US11222054B2 (en) Low-complexity methods for assessing distances between pairs of documents
Pietron et al. Retrain or not retrain?-efficient pruning methods of deep cnn networks
CN114049527B (zh) 基于在线协作与融合的自我知识蒸馏方法与系统
CN114118406A (zh) 一种卷积神经网络的量化压缩方法
CN113792621A (zh) 一种基于fpga的目标检测加速器设计方法
He et al. Learned transferable architectures can surpass hand-designed architectures for large scale speech recognition
CN112200310B (zh) 智能处理器、数据处理方法及存储介质
CN113870863A (zh) 声纹识别方法及装置、存储介质及电子设备
Zhou et al. AdaptCL: Efficient collaborative learning with dynamic and adaptive pruning
US20220027719A1 (en) Compressing tokens based on positions for transformer models
Cowen et al. Lsalsa: accelerated source separation via learned sparse coding
CN112487933A (zh) 一种基于自动化深度学习的雷达波形识别方法及系统
KR20230073757A (ko) 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법
CN112418388A (zh) 一种实现深度卷积神经网络处理的方法及装置
Liu et al. Flexi-compression: a flexible model compression method for autonomous driving
CN116957006A (zh) 预测模型的训练方法、装置、设备、介质及程序产品
US11954448B2 (en) Determining position values for transformer models