ELECTRONIC DEVICE FOR COMPRESSING CONVOLUTIONAL ARTIFICIAL INTELLIGENCE NEURAL NETWORK MODEL, AND CONTROL METHOD THEREOF

Provided are an electronic device and a method for compressing a convolutional artificial intelligence neural network (convolutional neural network (CNN)) model including a convolution layer by using the electronic device. The method may comprise the steps of: identifying a convolution tensor of at...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LEE, Youngyoon, LEE, Jaechool, YOU, Youngcheon, YEO, Jinsu, YUN, Jeongin
Format: Patent
Sprache:eng ; fre ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator LEE, Youngyoon
LEE, Jaechool
YOU, Youngcheon
YEO, Jinsu
YUN, Jeongin
description Provided are an electronic device and a method for compressing a convolutional artificial intelligence neural network (convolutional neural network (CNN)) model including a convolution layer by using the electronic device. The method may comprise the steps of: identifying a convolution tensor of at least one convolution layer; determining a direction in which tiling of the convolution tensor is performed, on the basis of a shape of the convolution tensor; generating a tile matrix from the convolution tensor according to the direction of tiling; performing low rank approximation (LRA) for the tile matrix to generate a U matrix and a V matrix; and generating a U convolution tensor through recombination of the U matrix, and generating a V convolution tensor through recombination of the V matrix. L'invention concerne un dispositif électronique et un procédé de compression d'un modèle de réseau neuronal à intelligence artificielle convolutif (réseau neuronal convolutif (CNN)) comprenant une couche de convolution en utilisant le dispositif électronique. Le procédé peut comprendre les étapes suivantes : identification d'un tenseur de convolution d'au moins une couche de convolution ; détermination d'une direction dans laquelle est effectuée la juxtaposition du tenseur de convolution, sur la base d'une forme du tenseur de convolution ; génération d'une matrice juxtaposition à partir du tenseur de convolution selon la direction de juxtaposition ; réalisation d'une approximation de rang bas (LRA) pour la matrice de juxtaposition afin de générer une matrice U et une matrice V ; et génération d'un tenseur de convolution U par recombinaison de la matrice U, et génération d'un tenseur de convolution V par recombinaison de la matrice V. 전자 장치 및 전자 장치를 이용하여 하나의 컨볼루션 레이어 (Convolution layer)를 포함하는 컨볼루션 인공지능 신경망 (Convolutional Neural Network, CNN) 모델을 압축하는 방법이 제공된다. 상기 방법은, 상기 적어도 하나의 컨볼루션 레이어의 컨볼루션 텐서(Convolution Tensor)를 식별하는 단계, 상기 컨볼루션 텐서의 모양에 기초하여 상기 컨볼루션 텐서를 타일링(tiling)하는 방향을 결정하는 단계, 상기 타일링하는 방향에 따라서, 상기 컨볼루션 텐서로부터 타일 행렬(Tile matrix)을 생성하는 단계, 상기 타일 행렬에 대해서 행렬 근사화(Low Rank Approximation, LRA)를 수행함으로써, U행렬 및 V행렬을 생성하는 단계 및 상기 U행렬을 재결합함으로써 U컨볼루션 텐서를 생성하고, 상기 V행렬을 재결합함으로써 V컨볼루션 텐서를 생성하는 단계를 포함할 수 있다.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2022108091A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2022108091A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2022108091A13</originalsourceid><addsrcrecordid>eNqNjbEKwkAQRNNYiPoPC7YKSWy0PO42yeJlVy6XpAxBzko0EAs_3xP8AKt5DPOYZfJGi9o7YdJgsCONUIgDLfXFYdMQl5G5E9t6ElYWlPNUkKaIxB6tpRI5Woytix2j78WdoRaDdgeKzdePBxZq9JUY8BU6lGKdLG7jfQ6bX66SbYFeV_swPYcwT-M1PMJr6CVP8zxLj-kpU9nhv9UHvgI7Mg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ELECTRONIC DEVICE FOR COMPRESSING CONVOLUTIONAL ARTIFICIAL INTELLIGENCE NEURAL NETWORK MODEL, AND CONTROL METHOD THEREOF</title><source>esp@cenet</source><creator>LEE, Youngyoon ; LEE, Jaechool ; YOU, Youngcheon ; YEO, Jinsu ; YUN, Jeongin</creator><creatorcontrib>LEE, Youngyoon ; LEE, Jaechool ; YOU, Youngcheon ; YEO, Jinsu ; YUN, Jeongin</creatorcontrib><description>Provided are an electronic device and a method for compressing a convolutional artificial intelligence neural network (convolutional neural network (CNN)) model including a convolution layer by using the electronic device. The method may comprise the steps of: identifying a convolution tensor of at least one convolution layer; determining a direction in which tiling of the convolution tensor is performed, on the basis of a shape of the convolution tensor; generating a tile matrix from the convolution tensor according to the direction of tiling; performing low rank approximation (LRA) for the tile matrix to generate a U matrix and a V matrix; and generating a U convolution tensor through recombination of the U matrix, and generating a V convolution tensor through recombination of the V matrix. L'invention concerne un dispositif électronique et un procédé de compression d'un modèle de réseau neuronal à intelligence artificielle convolutif (réseau neuronal convolutif (CNN)) comprenant une couche de convolution en utilisant le dispositif électronique. Le procédé peut comprendre les étapes suivantes : identification d'un tenseur de convolution d'au moins une couche de convolution ; détermination d'une direction dans laquelle est effectuée la juxtaposition du tenseur de convolution, sur la base d'une forme du tenseur de convolution ; génération d'une matrice juxtaposition à partir du tenseur de convolution selon la direction de juxtaposition ; réalisation d'une approximation de rang bas (LRA) pour la matrice de juxtaposition afin de générer une matrice U et une matrice V ; et génération d'un tenseur de convolution U par recombinaison de la matrice U, et génération d'un tenseur de convolution V par recombinaison de la matrice V. 전자 장치 및 전자 장치를 이용하여 하나의 컨볼루션 레이어 (Convolution layer)를 포함하는 컨볼루션 인공지능 신경망 (Convolutional Neural Network, CNN) 모델을 압축하는 방법이 제공된다. 상기 방법은, 상기 적어도 하나의 컨볼루션 레이어의 컨볼루션 텐서(Convolution Tensor)를 식별하는 단계, 상기 컨볼루션 텐서의 모양에 기초하여 상기 컨볼루션 텐서를 타일링(tiling)하는 방향을 결정하는 단계, 상기 타일링하는 방향에 따라서, 상기 컨볼루션 텐서로부터 타일 행렬(Tile matrix)을 생성하는 단계, 상기 타일 행렬에 대해서 행렬 근사화(Low Rank Approximation, LRA)를 수행함으로써, U행렬 및 V행렬을 생성하는 단계 및 상기 U행렬을 재결합함으로써 U컨볼루션 텐서를 생성하고, 상기 V행렬을 재결합함으로써 V컨볼루션 텐서를 생성하는 단계를 포함할 수 있다.</description><language>eng ; fre ; kor</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220527&amp;DB=EPODOC&amp;CC=WO&amp;NR=2022108091A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220527&amp;DB=EPODOC&amp;CC=WO&amp;NR=2022108091A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LEE, Youngyoon</creatorcontrib><creatorcontrib>LEE, Jaechool</creatorcontrib><creatorcontrib>YOU, Youngcheon</creatorcontrib><creatorcontrib>YEO, Jinsu</creatorcontrib><creatorcontrib>YUN, Jeongin</creatorcontrib><title>ELECTRONIC DEVICE FOR COMPRESSING CONVOLUTIONAL ARTIFICIAL INTELLIGENCE NEURAL NETWORK MODEL, AND CONTROL METHOD THEREOF</title><description>Provided are an electronic device and a method for compressing a convolutional artificial intelligence neural network (convolutional neural network (CNN)) model including a convolution layer by using the electronic device. The method may comprise the steps of: identifying a convolution tensor of at least one convolution layer; determining a direction in which tiling of the convolution tensor is performed, on the basis of a shape of the convolution tensor; generating a tile matrix from the convolution tensor according to the direction of tiling; performing low rank approximation (LRA) for the tile matrix to generate a U matrix and a V matrix; and generating a U convolution tensor through recombination of the U matrix, and generating a V convolution tensor through recombination of the V matrix. L'invention concerne un dispositif électronique et un procédé de compression d'un modèle de réseau neuronal à intelligence artificielle convolutif (réseau neuronal convolutif (CNN)) comprenant une couche de convolution en utilisant le dispositif électronique. Le procédé peut comprendre les étapes suivantes : identification d'un tenseur de convolution d'au moins une couche de convolution ; détermination d'une direction dans laquelle est effectuée la juxtaposition du tenseur de convolution, sur la base d'une forme du tenseur de convolution ; génération d'une matrice juxtaposition à partir du tenseur de convolution selon la direction de juxtaposition ; réalisation d'une approximation de rang bas (LRA) pour la matrice de juxtaposition afin de générer une matrice U et une matrice V ; et génération d'un tenseur de convolution U par recombinaison de la matrice U, et génération d'un tenseur de convolution V par recombinaison de la matrice V. 전자 장치 및 전자 장치를 이용하여 하나의 컨볼루션 레이어 (Convolution layer)를 포함하는 컨볼루션 인공지능 신경망 (Convolutional Neural Network, CNN) 모델을 압축하는 방법이 제공된다. 상기 방법은, 상기 적어도 하나의 컨볼루션 레이어의 컨볼루션 텐서(Convolution Tensor)를 식별하는 단계, 상기 컨볼루션 텐서의 모양에 기초하여 상기 컨볼루션 텐서를 타일링(tiling)하는 방향을 결정하는 단계, 상기 타일링하는 방향에 따라서, 상기 컨볼루션 텐서로부터 타일 행렬(Tile matrix)을 생성하는 단계, 상기 타일 행렬에 대해서 행렬 근사화(Low Rank Approximation, LRA)를 수행함으로써, U행렬 및 V행렬을 생성하는 단계 및 상기 U행렬을 재결합함으로써 U컨볼루션 텐서를 생성하고, 상기 V행렬을 재결합함으로써 V컨볼루션 텐서를 생성하는 단계를 포함할 수 있다.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjbEKwkAQRNNYiPoPC7YKSWy0PO42yeJlVy6XpAxBzko0EAs_3xP8AKt5DPOYZfJGi9o7YdJgsCONUIgDLfXFYdMQl5G5E9t6ElYWlPNUkKaIxB6tpRI5Woytix2j78WdoRaDdgeKzdePBxZq9JUY8BU6lGKdLG7jfQ6bX66SbYFeV_swPYcwT-M1PMJr6CVP8zxLj-kpU9nhv9UHvgI7Mg</recordid><startdate>20220527</startdate><enddate>20220527</enddate><creator>LEE, Youngyoon</creator><creator>LEE, Jaechool</creator><creator>YOU, Youngcheon</creator><creator>YEO, Jinsu</creator><creator>YUN, Jeongin</creator><scope>EVB</scope></search><sort><creationdate>20220527</creationdate><title>ELECTRONIC DEVICE FOR COMPRESSING CONVOLUTIONAL ARTIFICIAL INTELLIGENCE NEURAL NETWORK MODEL, AND CONTROL METHOD THEREOF</title><author>LEE, Youngyoon ; LEE, Jaechool ; YOU, Youngcheon ; YEO, Jinsu ; YUN, Jeongin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2022108091A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; kor</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>LEE, Youngyoon</creatorcontrib><creatorcontrib>LEE, Jaechool</creatorcontrib><creatorcontrib>YOU, Youngcheon</creatorcontrib><creatorcontrib>YEO, Jinsu</creatorcontrib><creatorcontrib>YUN, Jeongin</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LEE, Youngyoon</au><au>LEE, Jaechool</au><au>YOU, Youngcheon</au><au>YEO, Jinsu</au><au>YUN, Jeongin</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ELECTRONIC DEVICE FOR COMPRESSING CONVOLUTIONAL ARTIFICIAL INTELLIGENCE NEURAL NETWORK MODEL, AND CONTROL METHOD THEREOF</title><date>2022-05-27</date><risdate>2022</risdate><abstract>Provided are an electronic device and a method for compressing a convolutional artificial intelligence neural network (convolutional neural network (CNN)) model including a convolution layer by using the electronic device. The method may comprise the steps of: identifying a convolution tensor of at least one convolution layer; determining a direction in which tiling of the convolution tensor is performed, on the basis of a shape of the convolution tensor; generating a tile matrix from the convolution tensor according to the direction of tiling; performing low rank approximation (LRA) for the tile matrix to generate a U matrix and a V matrix; and generating a U convolution tensor through recombination of the U matrix, and generating a V convolution tensor through recombination of the V matrix. L'invention concerne un dispositif électronique et un procédé de compression d'un modèle de réseau neuronal à intelligence artificielle convolutif (réseau neuronal convolutif (CNN)) comprenant une couche de convolution en utilisant le dispositif électronique. Le procédé peut comprendre les étapes suivantes : identification d'un tenseur de convolution d'au moins une couche de convolution ; détermination d'une direction dans laquelle est effectuée la juxtaposition du tenseur de convolution, sur la base d'une forme du tenseur de convolution ; génération d'une matrice juxtaposition à partir du tenseur de convolution selon la direction de juxtaposition ; réalisation d'une approximation de rang bas (LRA) pour la matrice de juxtaposition afin de générer une matrice U et une matrice V ; et génération d'un tenseur de convolution U par recombinaison de la matrice U, et génération d'un tenseur de convolution V par recombinaison de la matrice V. 전자 장치 및 전자 장치를 이용하여 하나의 컨볼루션 레이어 (Convolution layer)를 포함하는 컨볼루션 인공지능 신경망 (Convolutional Neural Network, CNN) 모델을 압축하는 방법이 제공된다. 상기 방법은, 상기 적어도 하나의 컨볼루션 레이어의 컨볼루션 텐서(Convolution Tensor)를 식별하는 단계, 상기 컨볼루션 텐서의 모양에 기초하여 상기 컨볼루션 텐서를 타일링(tiling)하는 방향을 결정하는 단계, 상기 타일링하는 방향에 따라서, 상기 컨볼루션 텐서로부터 타일 행렬(Tile matrix)을 생성하는 단계, 상기 타일 행렬에 대해서 행렬 근사화(Low Rank Approximation, LRA)를 수행함으로써, U행렬 및 V행렬을 생성하는 단계 및 상기 U행렬을 재결합함으로써 U컨볼루션 텐서를 생성하고, 상기 V행렬을 재결합함으로써 V컨볼루션 텐서를 생성하는 단계를 포함할 수 있다.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; kor
recordid cdi_epo_espacenet_WO2022108091A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title ELECTRONIC DEVICE FOR COMPRESSING CONVOLUTIONAL ARTIFICIAL INTELLIGENCE NEURAL NETWORK MODEL, AND CONTROL METHOD THEREOF
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T21%3A54%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=LEE,%20Youngyoon&rft.date=2022-05-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2022108091A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true