TRAINING MACHINE LEARNING MODELS ON MULTIPLE MACHINE LEARNING TASKS
A method of training a machine learning model having multiple parameters, in which the machine learning model has been trained on a first machine learning task to determine first values of the parameters of the machine learning model. The method includes determining, for each of the parameters, a re...
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 | HADSELL, Raia Thais DESJARDINS, Guillaume RABINOWITZ, Neil Charles VENESS, Joel William PASCANU, Razvan KIRKPATRICK, James |
| description | A method of training a machine learning model having multiple parameters, in which the machine learning model has been trained on a first machine learning task to determine first values of the parameters of the machine learning model. The method includes determining, for each of the parameters, a respective measure of an importance of the parameter to the machine learning model achieving acceptable performance on the first machine learning task; obtaining training data for training the machine learning model on a second, different machine learning task; and training the machine learning model on the second machine learning task by training the machine learning model on the training data to adjust the first values of the parameters so that the machine learning model achieves an acceptable level of performance on the second machine learning task while maintaining an acceptable level of performance on the first machine learning task. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4231197A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4231197A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4231197A13</originalsourceid><addsrcrecordid>eNrjZHAOCXL09PP0c1fwdXT28PRzVfBxdQyCCPi7uPoEK_j7KfiG-oR4Bvi4YqoJcQz2DuZhYE1LzClO5YXS3AwKbq4hzh66qQX58anFBYnJqXmpJfGuASZGxoaGluaOhsZEKAEAznMrAQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>TRAINING MACHINE LEARNING MODELS ON MULTIPLE MACHINE LEARNING TASKS</title><source>esp@cenet</source><creator>HADSELL, Raia Thais ; DESJARDINS, Guillaume ; RABINOWITZ, Neil Charles ; VENESS, Joel William ; PASCANU, Razvan ; KIRKPATRICK, James</creator><creatorcontrib>HADSELL, Raia Thais ; DESJARDINS, Guillaume ; RABINOWITZ, Neil Charles ; VENESS, Joel William ; PASCANU, Razvan ; KIRKPATRICK, James</creatorcontrib><description>A method of training a machine learning model having multiple parameters, in which the machine learning model has been trained on a first machine learning task to determine first values of the parameters of the machine learning model. The method includes determining, for each of the parameters, a respective measure of an importance of the parameter to the machine learning model achieving acceptable performance on the first machine learning task; obtaining training data for training the machine learning model on a second, different machine learning task; and training the machine learning model on the second machine learning task by training the machine learning model on the training data to adjust the first values of the parameters so that the machine learning model achieves an acceptable level of performance on the second machine learning task while maintaining an acceptable level of performance on the first machine learning task.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2023</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=20230823&DB=EPODOC&CC=EP&NR=4231197A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230823&DB=EPODOC&CC=EP&NR=4231197A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HADSELL, Raia Thais</creatorcontrib><creatorcontrib>DESJARDINS, Guillaume</creatorcontrib><creatorcontrib>RABINOWITZ, Neil Charles</creatorcontrib><creatorcontrib>VENESS, Joel William</creatorcontrib><creatorcontrib>PASCANU, Razvan</creatorcontrib><creatorcontrib>KIRKPATRICK, James</creatorcontrib><title>TRAINING MACHINE LEARNING MODELS ON MULTIPLE MACHINE LEARNING TASKS</title><description>A method of training a machine learning model having multiple parameters, in which the machine learning model has been trained on a first machine learning task to determine first values of the parameters of the machine learning model. The method includes determining, for each of the parameters, a respective measure of an importance of the parameter to the machine learning model achieving acceptable performance on the first machine learning task; obtaining training data for training the machine learning model on a second, different machine learning task; and training the machine learning model on the second machine learning task by training the machine learning model on the training data to adjust the first values of the parameters so that the machine learning model achieves an acceptable level of performance on the second machine learning task while maintaining an acceptable level of performance on the first machine learning task.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHAOCXL09PP0c1fwdXT28PRzVfBxdQyCCPi7uPoEK_j7KfiG-oR4Bvi4YqoJcQz2DuZhYE1LzClO5YXS3AwKbq4hzh66qQX58anFBYnJqXmpJfGuASZGxoaGluaOhsZEKAEAznMrAQ</recordid><startdate>20230823</startdate><enddate>20230823</enddate><creator>HADSELL, Raia Thais</creator><creator>DESJARDINS, Guillaume</creator><creator>RABINOWITZ, Neil Charles</creator><creator>VENESS, Joel William</creator><creator>PASCANU, Razvan</creator><creator>KIRKPATRICK, James</creator><scope>EVB</scope></search><sort><creationdate>20230823</creationdate><title>TRAINING MACHINE LEARNING MODELS ON MULTIPLE MACHINE LEARNING TASKS</title><author>HADSELL, Raia Thais ; DESJARDINS, Guillaume ; RABINOWITZ, Neil Charles ; VENESS, Joel William ; PASCANU, Razvan ; KIRKPATRICK, James</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4231197A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2023</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>HADSELL, Raia Thais</creatorcontrib><creatorcontrib>DESJARDINS, Guillaume</creatorcontrib><creatorcontrib>RABINOWITZ, Neil Charles</creatorcontrib><creatorcontrib>VENESS, Joel William</creatorcontrib><creatorcontrib>PASCANU, Razvan</creatorcontrib><creatorcontrib>KIRKPATRICK, James</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HADSELL, Raia Thais</au><au>DESJARDINS, Guillaume</au><au>RABINOWITZ, Neil Charles</au><au>VENESS, Joel William</au><au>PASCANU, Razvan</au><au>KIRKPATRICK, James</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>TRAINING MACHINE LEARNING MODELS ON MULTIPLE MACHINE LEARNING TASKS</title><date>2023-08-23</date><risdate>2023</risdate><abstract>A method of training a machine learning model having multiple parameters, in which the machine learning model has been trained on a first machine learning task to determine first values of the parameters of the machine learning model. The method includes determining, for each of the parameters, a respective measure of an importance of the parameter to the machine learning model achieving acceptable performance on the first machine learning task; obtaining training data for training the machine learning model on a second, different machine learning task; and training the machine learning model on the second machine learning task by training the machine learning model on the training data to adjust the first values of the parameters so that the machine learning model achieves an acceptable level of performance on the second machine learning task while maintaining an acceptable level of performance on the first machine learning task.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; fre ; ger |
| recordid | cdi_epo_espacenet_EP4231197A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | TRAINING MACHINE LEARNING MODELS ON MULTIPLE MACHINE LEARNING TASKS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T16%3A52%3A55IST&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=HADSELL,%20Raia%20Thais&rft.date=2023-08-23&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4231197A1%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 |