PROGRESSIVE NEURALE NETZWERKE

Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the fi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: KAVUKCUOGLU, Koray, HADSELL, Raia Thais, SOYER, Hubert Josef, RABINOWITZ, Neil Charles, DESJARDINS, Guillaume, PASCANU, Razvan, KIRKPATRICK, James, RUSU, Andrei-Alexandru
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 KAVUKCUOGLU, Koray
HADSELL, Raia Thais
SOYER, Hubert Josef
RABINOWITZ, Neil Charles
DESJARDINS, Guillaume
PASCANU, Razvan
KIRKPATRICK, James
RUSU, Andrei-Alexandru
description Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4312157A2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4312157A2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4312157A23</originalsourceid><addsrcrecordid>eNrjZJANCPJ3D3INDvYMc1Xwcw0NcvQB0SFR4a5B3q48DKxpiTnFqbxQmptBwc01xNlDN7UgPz61uCAxOTUvtSTeNcDE2NDI0NTc0ciYCCUAdu4hAA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>PROGRESSIVE NEURALE NETZWERKE</title><source>esp@cenet</source><creator>KAVUKCUOGLU, Koray ; HADSELL, Raia Thais ; SOYER, Hubert Josef ; RABINOWITZ, Neil Charles ; DESJARDINS, Guillaume ; PASCANU, Razvan ; KIRKPATRICK, James ; RUSU, Andrei-Alexandru</creator><creatorcontrib>KAVUKCUOGLU, Koray ; HADSELL, Raia Thais ; SOYER, Hubert Josef ; RABINOWITZ, Neil Charles ; DESJARDINS, Guillaume ; PASCANU, Razvan ; KIRKPATRICK, James ; RUSU, Andrei-Alexandru</creatorcontrib><description>Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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&amp;date=20240131&amp;DB=EPODOC&amp;CC=EP&amp;NR=4312157A2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240131&amp;DB=EPODOC&amp;CC=EP&amp;NR=4312157A2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KAVUKCUOGLU, Koray</creatorcontrib><creatorcontrib>HADSELL, Raia Thais</creatorcontrib><creatorcontrib>SOYER, Hubert Josef</creatorcontrib><creatorcontrib>RABINOWITZ, Neil Charles</creatorcontrib><creatorcontrib>DESJARDINS, Guillaume</creatorcontrib><creatorcontrib>PASCANU, Razvan</creatorcontrib><creatorcontrib>KIRKPATRICK, James</creatorcontrib><creatorcontrib>RUSU, Andrei-Alexandru</creatorcontrib><title>PROGRESSIVE NEURALE NETZWERKE</title><description>Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZJANCPJ3D3INDvYMc1Xwcw0NcvQB0SFR4a5B3q48DKxpiTnFqbxQmptBwc01xNlDN7UgPz61uCAxOTUvtSTeNcDE2NDI0NTc0ciYCCUAdu4hAA</recordid><startdate>20240131</startdate><enddate>20240131</enddate><creator>KAVUKCUOGLU, Koray</creator><creator>HADSELL, Raia Thais</creator><creator>SOYER, Hubert Josef</creator><creator>RABINOWITZ, Neil Charles</creator><creator>DESJARDINS, Guillaume</creator><creator>PASCANU, Razvan</creator><creator>KIRKPATRICK, James</creator><creator>RUSU, Andrei-Alexandru</creator><scope>EVB</scope></search><sort><creationdate>20240131</creationdate><title>PROGRESSIVE NEURALE NETZWERKE</title><author>KAVUKCUOGLU, Koray ; HADSELL, Raia Thais ; SOYER, Hubert Josef ; RABINOWITZ, Neil Charles ; DESJARDINS, Guillaume ; PASCANU, Razvan ; KIRKPATRICK, James ; RUSU, Andrei-Alexandru</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4312157A23</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>KAVUKCUOGLU, Koray</creatorcontrib><creatorcontrib>HADSELL, Raia Thais</creatorcontrib><creatorcontrib>SOYER, Hubert Josef</creatorcontrib><creatorcontrib>RABINOWITZ, Neil Charles</creatorcontrib><creatorcontrib>DESJARDINS, Guillaume</creatorcontrib><creatorcontrib>PASCANU, Razvan</creatorcontrib><creatorcontrib>KIRKPATRICK, James</creatorcontrib><creatorcontrib>RUSU, Andrei-Alexandru</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KAVUKCUOGLU, Koray</au><au>HADSELL, Raia Thais</au><au>SOYER, Hubert Josef</au><au>RABINOWITZ, Neil Charles</au><au>DESJARDINS, Guillaume</au><au>PASCANU, Razvan</au><au>KIRKPATRICK, James</au><au>RUSU, Andrei-Alexandru</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>PROGRESSIVE NEURALE NETZWERKE</title><date>2024-01-31</date><risdate>2024</risdate><abstract>Methods and systems for performing a sequence of machine learning tasks. One system includes a sequence of deep neural networks (DNNs), including: a first DNN corresponding to a first machine learning task, wherein the first DNN comprises a first plurality of indexed layers, and each layer in the first plurality of indexed layers is configured to receive a respective layer input and process the layer input to generate a respective layer output; and one or more subsequent DNNs corresponding to one or more respective machine learning tasks, wherein each subsequent DNN comprises a respective plurality of indexed layers, and each layer in a respective plurality of indexed layers with index greater than one receives input from a preceding layer of the respective subsequent DNN, and one or more preceding layers of respective preceding DNNs, wherein a preceding layer is a layer whose index is one less than the current index.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4312157A2
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title PROGRESSIVE NEURALE NETZWERKE
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T18%3A55%3A12IST&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=KAVUKCUOGLU,%20Koray&rft.date=2024-01-31&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4312157A2%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