DATA PROCESSING METHOD AND APPARATUS FOR NEURAL NETWORK
Disclosed are a data processing method and apparatus for a neural network, which method and apparatus relate to the field of artificial intelligence. The method comprises: according to the data amount of input data, a first feature of an internal memory in a chip that runs a neural network, and a se...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; eng ; fre |
| 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 | YUAN, Honghui GAO, Shanqing GAO, Liwen XIONG, Lejin |
| description | Disclosed are a data processing method and apparatus for a neural network, which method and apparatus relate to the field of artificial intelligence. The method comprises: according to the data amount of input data, a first feature of an internal memory in a chip that runs a neural network, and a second feature of multiple layers in the neural network, dynamically segmenting the input data, and configuring different batch sizes for the layers in the neural network. By means of configuring a rational batch size for each layer in a neural network, during a neural network inference procedure, an internal memory can be fully utilized to store inter-layer data of the neural network, thereby improving the utilization rate of the internal memory, and ensuring the computational efficiency of hardware that runs the neural network.
Sont divulgués ici un procédé et un appareil de traitement de données d'un réseau neuronal qui se rapportent au domaine de l'intelligence artificielle. Le procédé consiste : en fonction de l |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_WO2021243489A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>WO2021243489A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_WO2021243489A13</originalsourceid><addsrcrecordid>eNrjZDB3cQxxVAgI8nd2DQ729HNX8HUN8fB3UXD0A-KAAMcgx5DQYAU3_yAFP9fQIEcfIBUS7h_kzcPAmpaYU5zKC6W5GZTdXEOcPXRTC_LjU4sLEpNT81JL4sP9jQyMDI1MjE0sLB0NjYlTBQDaqiko</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>DATA PROCESSING METHOD AND APPARATUS FOR NEURAL NETWORK</title><source>esp@cenet</source><creator>YUAN, Honghui ; GAO, Shanqing ; GAO, Liwen ; XIONG, Lejin</creator><creatorcontrib>YUAN, Honghui ; GAO, Shanqing ; GAO, Liwen ; XIONG, Lejin</creatorcontrib><description>Disclosed are a data processing method and apparatus for a neural network, which method and apparatus relate to the field of artificial intelligence. The method comprises: according to the data amount of input data, a first feature of an internal memory in a chip that runs a neural network, and a second feature of multiple layers in the neural network, dynamically segmenting the input data, and configuring different batch sizes for the layers in the neural network. By means of configuring a rational batch size for each layer in a neural network, during a neural network inference procedure, an internal memory can be fully utilized to store inter-layer data of the neural network, thereby improving the utilization rate of the internal memory, and ensuring the computational efficiency of hardware that runs the neural network.
Sont divulgués ici un procédé et un appareil de traitement de données d'un réseau neuronal qui se rapportent au domaine de l'intelligence artificielle. Le procédé consiste : en fonction de l</description><language>chi ; eng ; fre</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2021</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=20211209&DB=EPODOC&CC=WO&NR=2021243489A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20211209&DB=EPODOC&CC=WO&NR=2021243489A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YUAN, Honghui</creatorcontrib><creatorcontrib>GAO, Shanqing</creatorcontrib><creatorcontrib>GAO, Liwen</creatorcontrib><creatorcontrib>XIONG, Lejin</creatorcontrib><title>DATA PROCESSING METHOD AND APPARATUS FOR NEURAL NETWORK</title><description>Disclosed are a data processing method and apparatus for a neural network, which method and apparatus relate to the field of artificial intelligence. The method comprises: according to the data amount of input data, a first feature of an internal memory in a chip that runs a neural network, and a second feature of multiple layers in the neural network, dynamically segmenting the input data, and configuring different batch sizes for the layers in the neural network. By means of configuring a rational batch size for each layer in a neural network, during a neural network inference procedure, an internal memory can be fully utilized to store inter-layer data of the neural network, thereby improving the utilization rate of the internal memory, and ensuring the computational efficiency of hardware that runs the neural network.
Sont divulgués ici un procédé et un appareil de traitement de données d'un réseau neuronal qui se rapportent au domaine de l'intelligence artificielle. Le procédé consiste : en fonction de l</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>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDB3cQxxVAgI8nd2DQ729HNX8HUN8fB3UXD0A-KAAMcgx5DQYAU3_yAFP9fQIEcfIBUS7h_kzcPAmpaYU5zKC6W5GZTdXEOcPXRTC_LjU4sLEpNT81JL4sP9jQyMDI1MjE0sLB0NjYlTBQDaqiko</recordid><startdate>20211209</startdate><enddate>20211209</enddate><creator>YUAN, Honghui</creator><creator>GAO, Shanqing</creator><creator>GAO, Liwen</creator><creator>XIONG, Lejin</creator><scope>EVB</scope></search><sort><creationdate>20211209</creationdate><title>DATA PROCESSING METHOD AND APPARATUS FOR NEURAL NETWORK</title><author>YUAN, Honghui ; GAO, Shanqing ; GAO, Liwen ; XIONG, Lejin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_WO2021243489A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng ; fre</language><creationdate>2021</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>YUAN, Honghui</creatorcontrib><creatorcontrib>GAO, Shanqing</creatorcontrib><creatorcontrib>GAO, Liwen</creatorcontrib><creatorcontrib>XIONG, Lejin</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YUAN, Honghui</au><au>GAO, Shanqing</au><au>GAO, Liwen</au><au>XIONG, Lejin</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>DATA PROCESSING METHOD AND APPARATUS FOR NEURAL NETWORK</title><date>2021-12-09</date><risdate>2021</risdate><abstract>Disclosed are a data processing method and apparatus for a neural network, which method and apparatus relate to the field of artificial intelligence. The method comprises: according to the data amount of input data, a first feature of an internal memory in a chip that runs a neural network, and a second feature of multiple layers in the neural network, dynamically segmenting the input data, and configuring different batch sizes for the layers in the neural network. By means of configuring a rational batch size for each layer in a neural network, during a neural network inference procedure, an internal memory can be fully utilized to store inter-layer data of the neural network, thereby improving the utilization rate of the internal memory, and ensuring the computational efficiency of hardware that runs the neural network.
Sont divulgués ici un procédé et un appareil de traitement de données d'un réseau neuronal qui se rapportent au domaine de l'intelligence artificielle. Le procédé consiste : en fonction de l</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng ; fre |
| recordid | cdi_epo_espacenet_WO2021243489A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | DATA PROCESSING METHOD AND APPARATUS FOR NEURAL NETWORK |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T05%3A05%3A26IST&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=YUAN,%20Honghui&rft.date=2021-12-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EWO2021243489A1%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 |