MACHINE LEARNING DEVICE, INFERENCE DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM
An initialization rate determination unit (22) determines, in accordance with a depth of a layer in a neural network model, a first initialization rate for initializing weights in the neural network model on a first task. A machine learning execution unit (24) generates a neural network model traine...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; fre ; ger |
| 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 | KIDA Shingo TAKEHARA Hideki YANG Yincheng |
| description | An initialization rate determination unit (22) determines, in accordance with a depth of a layer in a neural network model, a first initialization rate for initializing weights in the neural network model on a first task. A machine learning execution unit (24) generates a neural network model trained on a first task by training on the first task by machine learning. An initialization unit (26) initializes weights in the neural network model trained on the first task, based on the first initialization rate, to generate an initialized neural network model trained on the first task, the initialized neural network trained on the first task being used in a second task. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4303773A4</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4303773A4</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4303773A43</originalsourceid><addsrcrecordid>eNrjZEjwdXT28PRzVfBxdQzy8_RzV3BxDfN0dtVR8PRzcw1y9XN2hYtgKPV1DfHwd9FRcPRzwZQMCPJ3D3L05WFgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8a4BJsYGxubmxo4mxkQoAQCopzI5</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MACHINE LEARNING DEVICE, INFERENCE DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM</title><source>esp@cenet</source><creator>KIDA Shingo ; TAKEHARA Hideki ; YANG Yincheng</creator><creatorcontrib>KIDA Shingo ; TAKEHARA Hideki ; YANG Yincheng</creatorcontrib><description>An initialization rate determination unit (22) determines, in accordance with a depth of a layer in a neural network model, a first initialization rate for initializing weights in the neural network model on a first task. A machine learning execution unit (24) generates a neural network model trained on a first task by training on the first task by machine learning. An initialization unit (26) initializes weights in the neural network model trained on the first task, based on the first initialization rate, to generate an initialized neural network model trained on the first task, the initialized neural network trained on the first task being used in a second task.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2024</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=20240731&DB=EPODOC&CC=EP&NR=4303773A4$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240731&DB=EPODOC&CC=EP&NR=4303773A4$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KIDA Shingo</creatorcontrib><creatorcontrib>TAKEHARA Hideki</creatorcontrib><creatorcontrib>YANG Yincheng</creatorcontrib><title>MACHINE LEARNING DEVICE, INFERENCE DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM</title><description>An initialization rate determination unit (22) determines, in accordance with a depth of a layer in a neural network model, a first initialization rate for initializing weights in the neural network model on a first task. A machine learning execution unit (24) generates a neural network model trained on a first task by training on the first task by machine learning. An initialization unit (26) initializes weights in the neural network model trained on the first task, based on the first initialization rate, to generate an initialized neural network model trained on the first task, the initialized neural network trained on the first task being used in a second task.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZEjwdXT28PRzVfBxdQzy8_RzV3BxDfN0dtVR8PRzcw1y9XN2hYtgKPV1DfHwd9FRcPRzwZQMCPJ3D3L05WFgTUvMKU7lhdLcDApuriHOHrqpBfnxqcUFicmpeakl8a4BJsYGxubmxo4mxkQoAQCopzI5</recordid><startdate>20240731</startdate><enddate>20240731</enddate><creator>KIDA Shingo</creator><creator>TAKEHARA Hideki</creator><creator>YANG Yincheng</creator><scope>EVB</scope></search><sort><creationdate>20240731</creationdate><title>MACHINE LEARNING DEVICE, INFERENCE DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM</title><author>KIDA Shingo ; TAKEHARA Hideki ; YANG Yincheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4303773A43</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>KIDA Shingo</creatorcontrib><creatorcontrib>TAKEHARA Hideki</creatorcontrib><creatorcontrib>YANG Yincheng</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KIDA Shingo</au><au>TAKEHARA Hideki</au><au>YANG Yincheng</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MACHINE LEARNING DEVICE, INFERENCE DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM</title><date>2024-07-31</date><risdate>2024</risdate><abstract>An initialization rate determination unit (22) determines, in accordance with a depth of a layer in a neural network model, a first initialization rate for initializing weights in the neural network model on a first task. A machine learning execution unit (24) generates a neural network model trained on a first task by training on the first task by machine learning. An initialization unit (26) initializes weights in the neural network model trained on the first task, based on the first initialization rate, to generate an initialized neural network model trained on the first task, the initialized neural network trained on the first task being used in a second task.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; fre ; ger |
| recordid | cdi_epo_espacenet_EP4303773A4 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | MACHINE LEARNING DEVICE, INFERENCE DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T03%3A18%3A01IST&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=KIDA%20Shingo&rft.date=2024-07-31&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4303773A4%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 |