DEEP NEURAL NETWORK SYSTEM
According to one embodiment of the present invention, a method for processing data of a deep neural network system comprises the steps of: receiving input data; generating first intermediate data by processing input data through a plurality of weight layers and generating second intermediate data by...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; 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 JIN HAN KIM YONG NYEON SUH IL HONG KO DONG WOOK |
| description | According to one embodiment of the present invention, a method for processing data of a deep neural network system comprises the steps of: receiving input data; generating first intermediate data by processing input data through a plurality of weight layers and generating second intermediate data by applying a linear function to input data; and summing the first intermediate data and second intermediate data, wherein the input data includes data of a plurality of feature maps.
본 발명의 일 실시예에 따른 심층 신경망(deep neural network) 시스템의 데이터 처리 방법은 입력 데이터를 수신하는 단계, 복수의 가중치 레이어(weight layer)를 통해 입력 데이터를 처리함으로써 제1 중간(intermediate) 데이터를 생성하고, 입력 데이터에 선형 함수를 적용함으로써 제2 중간 데이터를 생성하는 단계, 및 제1 중간 데이터 및 상기 제2 중간 데이터를 합하는 단계를 포함한다. 여기서, 입력 데이터는 복수의 특징 맵(feature map)의 데이터를 포함한다. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20190098402A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20190098402A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20190098402A3</originalsourceid><addsrcrecordid>eNrjZJBycXUNUPBzDQ1y9AFSIeH-Qd4KwZHBIa6-PAysaYk5xam8UJqbQdnNNcTZQze1ID8-tbggMTk1L7Uk3jvIyMDQ0sDA0sLEwMjRmDhVALjQITc</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>DEEP NEURAL NETWORK SYSTEM</title><source>esp@cenet</source><creator>LEE JIN HAN ; KIM YONG NYEON ; SUH IL HONG ; KO DONG WOOK</creator><creatorcontrib>LEE JIN HAN ; KIM YONG NYEON ; SUH IL HONG ; KO DONG WOOK</creatorcontrib><description>According to one embodiment of the present invention, a method for processing data of a deep neural network system comprises the steps of: receiving input data; generating first intermediate data by processing input data through a plurality of weight layers and generating second intermediate data by applying a linear function to input data; and summing the first intermediate data and second intermediate data, wherein the input data includes data of a plurality of feature maps.
본 발명의 일 실시예에 따른 심층 신경망(deep neural network) 시스템의 데이터 처리 방법은 입력 데이터를 수신하는 단계, 복수의 가중치 레이어(weight layer)를 통해 입력 데이터를 처리함으로써 제1 중간(intermediate) 데이터를 생성하고, 입력 데이터에 선형 함수를 적용함으로써 제2 중간 데이터를 생성하는 단계, 및 제1 중간 데이터 및 상기 제2 중간 데이터를 합하는 단계를 포함한다. 여기서, 입력 데이터는 복수의 특징 맵(feature map)의 데이터를 포함한다.</description><language>eng ; kor</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2019</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&date=20190822&DB=EPODOC&CC=KR&NR=20190098402A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190822&DB=EPODOC&CC=KR&NR=20190098402A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LEE JIN HAN</creatorcontrib><creatorcontrib>KIM YONG NYEON</creatorcontrib><creatorcontrib>SUH IL HONG</creatorcontrib><creatorcontrib>KO DONG WOOK</creatorcontrib><title>DEEP NEURAL NETWORK SYSTEM</title><description>According to one embodiment of the present invention, a method for processing data of a deep neural network system comprises the steps of: receiving input data; generating first intermediate data by processing input data through a plurality of weight layers and generating second intermediate data by applying a linear function to input data; and summing the first intermediate data and second intermediate data, wherein the input data includes data of a plurality of feature maps.
본 발명의 일 실시예에 따른 심층 신경망(deep neural network) 시스템의 데이터 처리 방법은 입력 데이터를 수신하는 단계, 복수의 가중치 레이어(weight layer)를 통해 입력 데이터를 처리함으로써 제1 중간(intermediate) 데이터를 생성하고, 입력 데이터에 선형 함수를 적용함으로써 제2 중간 데이터를 생성하는 단계, 및 제1 중간 데이터 및 상기 제2 중간 데이터를 합하는 단계를 포함한다. 여기서, 입력 데이터는 복수의 특징 맵(feature map)의 데이터를 포함한다.</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>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZJBycXUNUPBzDQ1y9AFSIeH-Qd4KwZHBIa6-PAysaYk5xam8UJqbQdnNNcTZQze1ID8-tbggMTk1L7Uk3jvIyMDQ0sDA0sLEwMjRmDhVALjQITc</recordid><startdate>20190822</startdate><enddate>20190822</enddate><creator>LEE JIN HAN</creator><creator>KIM YONG NYEON</creator><creator>SUH IL HONG</creator><creator>KO DONG WOOK</creator><scope>EVB</scope></search><sort><creationdate>20190822</creationdate><title>DEEP NEURAL NETWORK SYSTEM</title><author>LEE JIN HAN ; KIM YONG NYEON ; SUH IL HONG ; KO DONG WOOK</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20190098402A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</language><creationdate>2019</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 JIN HAN</creatorcontrib><creatorcontrib>KIM YONG NYEON</creatorcontrib><creatorcontrib>SUH IL HONG</creatorcontrib><creatorcontrib>KO DONG WOOK</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LEE JIN HAN</au><au>KIM YONG NYEON</au><au>SUH IL HONG</au><au>KO DONG WOOK</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>DEEP NEURAL NETWORK SYSTEM</title><date>2019-08-22</date><risdate>2019</risdate><abstract>According to one embodiment of the present invention, a method for processing data of a deep neural network system comprises the steps of: receiving input data; generating first intermediate data by processing input data through a plurality of weight layers and generating second intermediate data by applying a linear function to input data; and summing the first intermediate data and second intermediate data, wherein the input data includes data of a plurality of feature maps.
본 발명의 일 실시예에 따른 심층 신경망(deep neural network) 시스템의 데이터 처리 방법은 입력 데이터를 수신하는 단계, 복수의 가중치 레이어(weight layer)를 통해 입력 데이터를 처리함으로써 제1 중간(intermediate) 데이터를 생성하고, 입력 데이터에 선형 함수를 적용함으로써 제2 중간 데이터를 생성하는 단계, 및 제1 중간 데이터 및 상기 제2 중간 데이터를 합하는 단계를 포함한다. 여기서, 입력 데이터는 복수의 특징 맵(feature map)의 데이터를 포함한다.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; kor |
| recordid | cdi_epo_espacenet_KR20190098402A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | DEEP NEURAL NETWORK SYSTEM |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-27T20%3A57%3A43IST&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%20JIN%20HAN&rft.date=2019-08-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20190098402A%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 |