Neural network model training system and method
The invention relates to a neural network model training system and method. The system comprises a coordination device and a preset number of computation devices, wherein the coordination device is used for performing synchronous control on the computation devices according to the layers of a neural...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng |
| 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 | GUO ZHIMAO ZOU YONGQIANG JIN XING LI YI |
| description | The invention relates to a neural network model training system and method. The system comprises a coordination device and a preset number of computation devices, wherein the coordination device is used for performing synchronous control on the computation devices according to the layers of a neural network model; each computation device is used for processing a node distributed to each computation device in the corresponding layer of the neural network model according to a training sequence of the neural network model and a training sample input to the neural network model under the synchronous control of the coordination device according to the layers of the neural network model, and sending data generated by node processing to a model storage device or the computation device which the next-layer node connected with the node of current device is located at until the training of the input training sample is ended. The neural network model training system and method provided by the invention solve the problem of scale limitation of the neural network model caused by limitation of a single physical device. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN104978601A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN104978601A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN104978601A3</originalsourceid><addsrcrecordid>eNrjZND3Sy0tSsxRyEstKc8vylbIzU9JzVEoKUrMzMvMS1coriwuSc1VSMxLUchNLcnIT-FhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqUCj4p39DA1MLM0tzAwMHY2JUQMAP8ErFQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Neural network model training system and method</title><source>esp@cenet</source><creator>GUO ZHIMAO ; ZOU YONGQIANG ; JIN XING ; LI YI</creator><creatorcontrib>GUO ZHIMAO ; ZOU YONGQIANG ; JIN XING ; LI YI</creatorcontrib><description>The invention relates to a neural network model training system and method. The system comprises a coordination device and a preset number of computation devices, wherein the coordination device is used for performing synchronous control on the computation devices according to the layers of a neural network model; each computation device is used for processing a node distributed to each computation device in the corresponding layer of the neural network model according to a training sequence of the neural network model and a training sample input to the neural network model under the synchronous control of the coordination device according to the layers of the neural network model, and sending data generated by node processing to a model storage device or the computation device which the next-layer node connected with the node of current device is located at until the training of the input training sample is ended. The neural network model training system and method provided by the invention solve the problem of scale limitation of the neural network model caused by limitation of a single physical device.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2015</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=20151014&DB=EPODOC&CC=CN&NR=104978601A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20151014&DB=EPODOC&CC=CN&NR=104978601A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>GUO ZHIMAO</creatorcontrib><creatorcontrib>ZOU YONGQIANG</creatorcontrib><creatorcontrib>JIN XING</creatorcontrib><creatorcontrib>LI YI</creatorcontrib><title>Neural network model training system and method</title><description>The invention relates to a neural network model training system and method. The system comprises a coordination device and a preset number of computation devices, wherein the coordination device is used for performing synchronous control on the computation devices according to the layers of a neural network model; each computation device is used for processing a node distributed to each computation device in the corresponding layer of the neural network model according to a training sequence of the neural network model and a training sample input to the neural network model under the synchronous control of the coordination device according to the layers of the neural network model, and sending data generated by node processing to a model storage device or the computation device which the next-layer node connected with the node of current device is located at until the training of the input training sample is ended. The neural network model training system and method provided by the invention solve the problem of scale limitation of the neural network model caused by limitation of a single physical device.</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>2015</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZND3Sy0tSsxRyEstKc8vylbIzU9JzVEoKUrMzMvMS1coriwuSc1VSMxLUchNLcnIT-FhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqUCj4p39DA1MLM0tzAwMHY2JUQMAP8ErFQ</recordid><startdate>20151014</startdate><enddate>20151014</enddate><creator>GUO ZHIMAO</creator><creator>ZOU YONGQIANG</creator><creator>JIN XING</creator><creator>LI YI</creator><scope>EVB</scope></search><sort><creationdate>20151014</creationdate><title>Neural network model training system and method</title><author>GUO ZHIMAO ; ZOU YONGQIANG ; JIN XING ; LI YI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN104978601A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2015</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>GUO ZHIMAO</creatorcontrib><creatorcontrib>ZOU YONGQIANG</creatorcontrib><creatorcontrib>JIN XING</creatorcontrib><creatorcontrib>LI YI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>GUO ZHIMAO</au><au>ZOU YONGQIANG</au><au>JIN XING</au><au>LI YI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Neural network model training system and method</title><date>2015-10-14</date><risdate>2015</risdate><abstract>The invention relates to a neural network model training system and method. The system comprises a coordination device and a preset number of computation devices, wherein the coordination device is used for performing synchronous control on the computation devices according to the layers of a neural network model; each computation device is used for processing a node distributed to each computation device in the corresponding layer of the neural network model according to a training sequence of the neural network model and a training sample input to the neural network model under the synchronous control of the coordination device according to the layers of the neural network model, and sending data generated by node processing to a model storage device or the computation device which the next-layer node connected with the node of current device is located at until the training of the input training sample is ended. The neural network model training system and method provided by the invention solve the problem of scale limitation of the neural network model caused by limitation of a single physical device.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_CN104978601A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Neural network model training system and method |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-15T22%3A40%3A18IST&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=GUO%20ZHIMAO&rft.date=2015-10-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN104978601A%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 |