Machine learning system and machine learning method
A machine learning system includes a host device and several client devices. The client devices receive a host model from the host device, respectively, and include a first and a second client devices. The first and the second client devices store a first and a second parameter sets, respectively, a...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; 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 | WANG, PING-FENG HSU, KENG-JUI HSU, CHIUN-SHENG CHOU, JERRY CHI-YUAN |
| description | A machine learning system includes a host device and several client devices. The client devices receive a host model from the host device, respectively, and include a first and a second client devices. The first and the second client devices store a first and a second parameter sets, respectively, and perform training on the received host models according to the first and the second parameter sets, respectively, to respectively generate a first and a second training results. If the host device has received the first training result corresponding to an m-th training round but has not received the second training result corresponding to a n-th round training, when a difference between m and n is not higher than a threshold value, the host device updates the host model according to the first training result without using the second training result. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_TWI777262BB</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>TWI777262BB</sourcerecordid><originalsourceid>FETCH-epo_espacenet_TWI777262BB3</originalsourceid><addsrcrecordid>eNrjZDD2TUzOyMxLVchJTSzKy8xLVyiuLC5JzVVIzEtRyEWXy00tychP4WFgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8SHhnubm5kZmRk5OxkQoAQCu_iyF</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Machine learning system and machine learning method</title><source>esp@cenet</source><creator>WANG, PING-FENG ; HSU, KENG-JUI ; HSU, CHIUN-SHENG ; CHOU, JERRY CHI-YUAN</creator><creatorcontrib>WANG, PING-FENG ; HSU, KENG-JUI ; HSU, CHIUN-SHENG ; CHOU, JERRY CHI-YUAN</creatorcontrib><description>A machine learning system includes a host device and several client devices. The client devices receive a host model from the host device, respectively, and include a first and a second client devices. The first and the second client devices store a first and a second parameter sets, respectively, and perform training on the received host models according to the first and the second parameter sets, respectively, to respectively generate a first and a second training results. If the host device has received the first training result corresponding to an m-th training round but has not received the second training result corresponding to a n-th round training, when a difference between m and n is not higher than a threshold value, the host device updates the host model according to the first training result without using the second training result.</description><language>chi ; eng</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&date=20220911&DB=EPODOC&CC=TW&NR=I777262B$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220911&DB=EPODOC&CC=TW&NR=I777262B$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG, PING-FENG</creatorcontrib><creatorcontrib>HSU, KENG-JUI</creatorcontrib><creatorcontrib>HSU, CHIUN-SHENG</creatorcontrib><creatorcontrib>CHOU, JERRY CHI-YUAN</creatorcontrib><title>Machine learning system and machine learning method</title><description>A machine learning system includes a host device and several client devices. The client devices receive a host model from the host device, respectively, and include a first and a second client devices. The first and the second client devices store a first and a second parameter sets, respectively, and perform training on the received host models according to the first and the second parameter sets, respectively, to respectively generate a first and a second training results. If the host device has received the first training result corresponding to an m-th training round but has not received the second training result corresponding to a n-th round training, when a difference between m and n is not higher than a threshold value, the host device updates the host model according to the first training result without using the second training result.</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>eNrjZDD2TUzOyMxLVchJTSzKy8xLVyiuLC5JzVVIzEtRyEWXy00tychP4WFgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8SHhnubm5kZmRk5OxkQoAQCu_iyF</recordid><startdate>20220911</startdate><enddate>20220911</enddate><creator>WANG, PING-FENG</creator><creator>HSU, KENG-JUI</creator><creator>HSU, CHIUN-SHENG</creator><creator>CHOU, JERRY CHI-YUAN</creator><scope>EVB</scope></search><sort><creationdate>20220911</creationdate><title>Machine learning system and machine learning method</title><author>WANG, PING-FENG ; HSU, KENG-JUI ; HSU, CHIUN-SHENG ; CHOU, JERRY CHI-YUAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_TWI777262BB3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</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>WANG, PING-FENG</creatorcontrib><creatorcontrib>HSU, KENG-JUI</creatorcontrib><creatorcontrib>HSU, CHIUN-SHENG</creatorcontrib><creatorcontrib>CHOU, JERRY CHI-YUAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG, PING-FENG</au><au>HSU, KENG-JUI</au><au>HSU, CHIUN-SHENG</au><au>CHOU, JERRY CHI-YUAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Machine learning system and machine learning method</title><date>2022-09-11</date><risdate>2022</risdate><abstract>A machine learning system includes a host device and several client devices. The client devices receive a host model from the host device, respectively, and include a first and a second client devices. The first and the second client devices store a first and a second parameter sets, respectively, and perform training on the received host models according to the first and the second parameter sets, respectively, to respectively generate a first and a second training results. If the host device has received the first training result corresponding to an m-th training round but has not received the second training result corresponding to a n-th round training, when a difference between m and n is not higher than a threshold value, the host device updates the host model according to the first training result without using the second training result.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_TWI777262BB |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Machine learning system and machine learning method |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T02%3A29%3A39IST&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=WANG,%20PING-FENG&rft.date=2022-09-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ETWI777262BB%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 |