Deep multi-task representation learning
Technologies for analyzing multi-task multimodal data to detect multi-task multimodal events using a deep multi-task representation learning, are disclosed. A combined model with both generative and discriminative aspects is used to share information during both generative and discriminative process...
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 | Tamrakar, Amir Ehrlich, Max Almaev, Timur Amer, Mohamed R Shields, Timothy J |
| description | Technologies for analyzing multi-task multimodal data to detect multi-task multimodal events using a deep multi-task representation learning, are disclosed. A combined model with both generative and discriminative aspects is used to share information during both generative and discriminative processes. The technologies can be used to classify data and also to generate data from classification events. The data can then be used to morph data into a desired classification event. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US12073305B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US12073305B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US12073305B23</originalsourceid><addsrcrecordid>eNrjZFB3SU0tUMgtzSnJ1C1JLM5WKEotKEotTs0rSSzJzM9TyElNLMrLzEvnYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxocGGRgbmxsYGpk5GxsSoAQC__yhY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Deep multi-task representation learning</title><source>esp@cenet</source><creator>Tamrakar, Amir ; Ehrlich, Max ; Almaev, Timur ; Amer, Mohamed R ; Shields, Timothy J</creator><creatorcontrib>Tamrakar, Amir ; Ehrlich, Max ; Almaev, Timur ; Amer, Mohamed R ; Shields, Timothy J</creatorcontrib><description>Technologies for analyzing multi-task multimodal data to detect multi-task multimodal events using a deep multi-task representation learning, are disclosed. A combined model with both generative and discriminative aspects is used to share information during both generative and discriminative processes. The technologies can be used to classify data and also to generate data from classification events. The data can then be used to morph data into a desired classification event.</description><language>eng</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=20240827&DB=EPODOC&CC=US&NR=12073305B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240827&DB=EPODOC&CC=US&NR=12073305B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Tamrakar, Amir</creatorcontrib><creatorcontrib>Ehrlich, Max</creatorcontrib><creatorcontrib>Almaev, Timur</creatorcontrib><creatorcontrib>Amer, Mohamed R</creatorcontrib><creatorcontrib>Shields, Timothy J</creatorcontrib><title>Deep multi-task representation learning</title><description>Technologies for analyzing multi-task multimodal data to detect multi-task multimodal events using a deep multi-task representation learning, are disclosed. A combined model with both generative and discriminative aspects is used to share information during both generative and discriminative processes. The technologies can be used to classify data and also to generate data from classification events. The data can then be used to morph data into a desired classification event.</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>eNrjZFB3SU0tUMgtzSnJ1C1JLM5WKEotKEotTs0rSSzJzM9TyElNLMrLzEvnYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxocGGRgbmxsYGpk5GxsSoAQC__yhY</recordid><startdate>20240827</startdate><enddate>20240827</enddate><creator>Tamrakar, Amir</creator><creator>Ehrlich, Max</creator><creator>Almaev, Timur</creator><creator>Amer, Mohamed R</creator><creator>Shields, Timothy J</creator><scope>EVB</scope></search><sort><creationdate>20240827</creationdate><title>Deep multi-task representation learning</title><author>Tamrakar, Amir ; Ehrlich, Max ; Almaev, Timur ; Amer, Mohamed R ; Shields, Timothy J</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US12073305B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</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>Tamrakar, Amir</creatorcontrib><creatorcontrib>Ehrlich, Max</creatorcontrib><creatorcontrib>Almaev, Timur</creatorcontrib><creatorcontrib>Amer, Mohamed R</creatorcontrib><creatorcontrib>Shields, Timothy J</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tamrakar, Amir</au><au>Ehrlich, Max</au><au>Almaev, Timur</au><au>Amer, Mohamed R</au><au>Shields, Timothy J</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Deep multi-task representation learning</title><date>2024-08-27</date><risdate>2024</risdate><abstract>Technologies for analyzing multi-task multimodal data to detect multi-task multimodal events using a deep multi-task representation learning, are disclosed. A combined model with both generative and discriminative aspects is used to share information during both generative and discriminative processes. The technologies can be used to classify data and also to generate data from classification events. The data can then be used to morph data into a desired classification event.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US12073305B2 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | Deep multi-task representation learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T20%3A11%3A33IST&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=Tamrakar,%20Amir&rft.date=2024-08-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS12073305B2%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 |