NEURAL NETWORK ARCHITECTURE SEARCH OVER COMPLEX BLOCK ARCHITECTURES
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing neural architecture search for machine learning models. In one aspect, a method comprises receiving training data for a machine learning, generating a plurality of candidate neural netwo...
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 | Zhou, Yanqi So, David Richard Lan, Chang Cui, Yingwei Shakeri, Siamak Le, Quoc V Huang, Da Chen, Zhifeng Laudon, James Peng, Daiyi Huang, Yanping Lu, Yifeng Dai, Andrew M Du, Nan Dean, Jeffrey Adgate |
| description | Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing neural architecture search for machine learning models. In one aspect, a method comprises receiving training data for a machine learning, generating a plurality of candidate neural networks for performing the machine learning task, wherein each candidate neural network comprises a plurality of instances of a layer block composed of a plurality of layers, for each candidate neural network, selecting a respective type for each of the plurality of layers from a set of layer types that comprises, training the candidate neural network and evaluating performance scores for the trained candidate neural networks as applied to the machine learning task, and determining a final neural network for performing the machine learning task based at least on the performance scores for the candidate neural networks. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024112027A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024112027A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024112027A13</originalsourceid><addsrcrecordid>eNrjZHD2cw0NcvRR8HMNCfcP8lZwDHL28AxxdQ4JDXJVCHYFcRX8w1yDFJz9fQN8XCMUnHz8nVGVBfMwsKYl5hSn8kJpbgZlN9cQZw_d1IL8-NTigsTk1LzUkvjQYCMDIxNDQyBp7mhoTJwqAAA7LKc</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>NEURAL NETWORK ARCHITECTURE SEARCH OVER COMPLEX BLOCK ARCHITECTURES</title><source>esp@cenet</source><creator>Zhou, Yanqi ; So, David Richard ; Lan, Chang ; Cui, Yingwei ; Shakeri, Siamak ; Le, Quoc V ; Huang, Da ; Chen, Zhifeng ; Laudon, James ; Peng, Daiyi ; Huang, Yanping ; Lu, Yifeng ; Dai, Andrew M ; Du, Nan ; Dean, Jeffrey Adgate</creator><creatorcontrib>Zhou, Yanqi ; So, David Richard ; Lan, Chang ; Cui, Yingwei ; Shakeri, Siamak ; Le, Quoc V ; Huang, Da ; Chen, Zhifeng ; Laudon, James ; Peng, Daiyi ; Huang, Yanping ; Lu, Yifeng ; Dai, Andrew M ; Du, Nan ; Dean, Jeffrey Adgate</creatorcontrib><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing neural architecture search for machine learning models. In one aspect, a method comprises receiving training data for a machine learning, generating a plurality of candidate neural networks for performing the machine learning task, wherein each candidate neural network comprises a plurality of instances of a layer block composed of a plurality of layers, for each candidate neural network, selecting a respective type for each of the plurality of layers from a set of layer types that comprises, training the candidate neural network and evaluating performance scores for the trained candidate neural networks as applied to the machine learning task, and determining a final neural network for performing the machine learning task based at least on the performance scores for the candidate neural networks.</description><language>eng</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&date=20240404&DB=EPODOC&CC=US&NR=2024112027A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240404&DB=EPODOC&CC=US&NR=2024112027A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Zhou, Yanqi</creatorcontrib><creatorcontrib>So, David Richard</creatorcontrib><creatorcontrib>Lan, Chang</creatorcontrib><creatorcontrib>Cui, Yingwei</creatorcontrib><creatorcontrib>Shakeri, Siamak</creatorcontrib><creatorcontrib>Le, Quoc V</creatorcontrib><creatorcontrib>Huang, Da</creatorcontrib><creatorcontrib>Chen, Zhifeng</creatorcontrib><creatorcontrib>Laudon, James</creatorcontrib><creatorcontrib>Peng, Daiyi</creatorcontrib><creatorcontrib>Huang, Yanping</creatorcontrib><creatorcontrib>Lu, Yifeng</creatorcontrib><creatorcontrib>Dai, Andrew M</creatorcontrib><creatorcontrib>Du, Nan</creatorcontrib><creatorcontrib>Dean, Jeffrey Adgate</creatorcontrib><title>NEURAL NETWORK ARCHITECTURE SEARCH OVER COMPLEX BLOCK ARCHITECTURES</title><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing neural architecture search for machine learning models. In one aspect, a method comprises receiving training data for a machine learning, generating a plurality of candidate neural networks for performing the machine learning task, wherein each candidate neural network comprises a plurality of instances of a layer block composed of a plurality of layers, for each candidate neural network, selecting a respective type for each of the plurality of layers from a set of layer types that comprises, training the candidate neural network and evaluating performance scores for the trained candidate neural networks as applied to the machine learning task, and determining a final neural network for performing the machine learning task based at least on the performance scores for the candidate neural networks.</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>eNrjZHD2cw0NcvRR8HMNCfcP8lZwDHL28AxxdQ4JDXJVCHYFcRX8w1yDFJz9fQN8XCMUnHz8nVGVBfMwsKYl5hSn8kJpbgZlN9cQZw_d1IL8-NTigsTk1LzUkvjQYCMDIxNDQyBp7mhoTJwqAAA7LKc</recordid><startdate>20240404</startdate><enddate>20240404</enddate><creator>Zhou, Yanqi</creator><creator>So, David Richard</creator><creator>Lan, Chang</creator><creator>Cui, Yingwei</creator><creator>Shakeri, Siamak</creator><creator>Le, Quoc V</creator><creator>Huang, Da</creator><creator>Chen, Zhifeng</creator><creator>Laudon, James</creator><creator>Peng, Daiyi</creator><creator>Huang, Yanping</creator><creator>Lu, Yifeng</creator><creator>Dai, Andrew M</creator><creator>Du, Nan</creator><creator>Dean, Jeffrey Adgate</creator><scope>EVB</scope></search><sort><creationdate>20240404</creationdate><title>NEURAL NETWORK ARCHITECTURE SEARCH OVER COMPLEX BLOCK ARCHITECTURES</title><author>Zhou, Yanqi ; So, David Richard ; Lan, Chang ; Cui, Yingwei ; Shakeri, Siamak ; Le, Quoc V ; Huang, Da ; Chen, Zhifeng ; Laudon, James ; Peng, Daiyi ; Huang, Yanping ; Lu, Yifeng ; Dai, Andrew M ; Du, Nan ; Dean, Jeffrey Adgate</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024112027A13</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhou, Yanqi</creatorcontrib><creatorcontrib>So, David Richard</creatorcontrib><creatorcontrib>Lan, Chang</creatorcontrib><creatorcontrib>Cui, Yingwei</creatorcontrib><creatorcontrib>Shakeri, Siamak</creatorcontrib><creatorcontrib>Le, Quoc V</creatorcontrib><creatorcontrib>Huang, Da</creatorcontrib><creatorcontrib>Chen, Zhifeng</creatorcontrib><creatorcontrib>Laudon, James</creatorcontrib><creatorcontrib>Peng, Daiyi</creatorcontrib><creatorcontrib>Huang, Yanping</creatorcontrib><creatorcontrib>Lu, Yifeng</creatorcontrib><creatorcontrib>Dai, Andrew M</creatorcontrib><creatorcontrib>Du, Nan</creatorcontrib><creatorcontrib>Dean, Jeffrey Adgate</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zhou, Yanqi</au><au>So, David Richard</au><au>Lan, Chang</au><au>Cui, Yingwei</au><au>Shakeri, Siamak</au><au>Le, Quoc V</au><au>Huang, Da</au><au>Chen, Zhifeng</au><au>Laudon, James</au><au>Peng, Daiyi</au><au>Huang, Yanping</au><au>Lu, Yifeng</au><au>Dai, Andrew M</au><au>Du, Nan</au><au>Dean, Jeffrey Adgate</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>NEURAL NETWORK ARCHITECTURE SEARCH OVER COMPLEX BLOCK ARCHITECTURES</title><date>2024-04-04</date><risdate>2024</risdate><abstract>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing neural architecture search for machine learning models. In one aspect, a method comprises receiving training data for a machine learning, generating a plurality of candidate neural networks for performing the machine learning task, wherein each candidate neural network comprises a plurality of instances of a layer block composed of a plurality of layers, for each candidate neural network, selecting a respective type for each of the plurality of layers from a set of layer types that comprises, training the candidate neural network and evaluating performance scores for the trained candidate neural networks as applied to the machine learning task, and determining a final neural network for performing the machine learning task based at least on the performance scores for the candidate neural networks.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2024112027A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | NEURAL NETWORK ARCHITECTURE SEARCH OVER COMPLEX BLOCK ARCHITECTURES |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T20%3A45%3A57IST&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=Zhou,%20Yanqi&rft.date=2024-04-04&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024112027A1%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 |