Three-dimensional (3D) convolution with 3D batch normalization

Three-dimensional (3D) convolution with 3D batch normalization

A method of classifying three-dimensional (3D) data includes receiving three-dimensional (3D) data and processing the 3D data using a neural network that includes a plurality of subnetworks arranged in a sequence and the data is processed through each of the subnetworks. Each of the subnetworks is c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Socher, Richard, Xiong, Caiming, Tai, Kai Sheng
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
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 Socher, Richard
Xiong, Caiming
Tai, Kai Sheng
description A method of classifying three-dimensional (3D) data includes receiving three-dimensional (3D) data and processing the 3D data using a neural network that includes a plurality of subnetworks arranged in a sequence and the data is processed through each of the subnetworks. Each of the subnetworks is configured to receive an output generated by a preceding subnetwork in the sequence, process the output through a plurality of parallel 3D convolution layer paths of varying convolution volume, process the output through a parallel pooling path, and concatenate output of the 3D convolution layer paths and the pooling path to generate an output representation from each of the subnetworks. Following processing the data through the subnetworks, the method includes processing the output of a last one of the subnetworks in the sequence through a vertical pooling layer to generate an output and classifying the received 3D data based upon the generated output.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11416747B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11416747B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11416747B23</originalsourceid><addsrcrecordid>eNrjZLALyShKTdVNycxNzSvOzM9LzFHQMHbRVEjOzyvLzyktAQoplGeWZCgYuygkJZYkZyjk5RflJuZkViWC5HgYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyal5qSXxosKGhiaGZuYm5k5ExMWoABMkwEw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Three-dimensional (3D) convolution with 3D batch normalization</title><source>esp@cenet</source><creator>Socher, Richard ; Xiong, Caiming ; Tai, Kai Sheng</creator><creatorcontrib>Socher, Richard ; Xiong, Caiming ; Tai, Kai Sheng</creatorcontrib><description>A method of classifying three-dimensional (3D) data includes receiving three-dimensional (3D) data and processing the 3D data using a neural network that includes a plurality of subnetworks arranged in a sequence and the data is processed through each of the subnetworks. Each of the subnetworks is configured to receive an output generated by a preceding subnetwork in the sequence, process the output through a plurality of parallel 3D convolution layer paths of varying convolution volume, process the output through a parallel pooling path, and concatenate output of the 3D convolution layer paths and the pooling path to generate an output representation from each of the subnetworks. Following processing the data through the subnetworks, the method includes processing the output of a last one of the subnetworks in the sequence through a vertical pooling layer to generate an output and classifying the received 3D data based upon the generated output.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2022</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=20220816&amp;DB=EPODOC&amp;CC=US&amp;NR=11416747B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220816&amp;DB=EPODOC&amp;CC=US&amp;NR=11416747B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Socher, Richard</creatorcontrib><creatorcontrib>Xiong, Caiming</creatorcontrib><creatorcontrib>Tai, Kai Sheng</creatorcontrib><title>Three-dimensional (3D) convolution with 3D batch normalization</title><description>A method of classifying three-dimensional (3D) data includes receiving three-dimensional (3D) data and processing the 3D data using a neural network that includes a plurality of subnetworks arranged in a sequence and the data is processed through each of the subnetworks. Each of the subnetworks is configured to receive an output generated by a preceding subnetwork in the sequence, process the output through a plurality of parallel 3D convolution layer paths of varying convolution volume, process the output through a parallel pooling path, and concatenate output of the 3D convolution layer paths and the pooling path to generate an output representation from each of the subnetworks. Following processing the data through the subnetworks, the method includes processing the output of a last one of the subnetworks in the sequence through a vertical pooling layer to generate an output and classifying the received 3D data based upon the generated output.</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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLALyShKTdVNycxNzSvOzM9LzFHQMHbRVEjOzyvLzyktAQoplGeWZCgYuygkJZYkZyjk5RflJuZkViWC5HgYWNMSc4pTeaE0N4Oim2uIs4duakF-fGpxQWJyal5qSXxosKGhiaGZuYm5k5ExMWoABMkwEw</recordid><startdate>20220816</startdate><enddate>20220816</enddate><creator>Socher, Richard</creator><creator>Xiong, Caiming</creator><creator>Tai, Kai Sheng</creator><scope>EVB</scope></search><sort><creationdate>20220816</creationdate><title>Three-dimensional (3D) convolution with 3D batch normalization</title><author>Socher, Richard ; Xiong, Caiming ; Tai, Kai Sheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11416747B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2022</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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Socher, Richard</creatorcontrib><creatorcontrib>Xiong, Caiming</creatorcontrib><creatorcontrib>Tai, Kai Sheng</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Socher, Richard</au><au>Xiong, Caiming</au><au>Tai, Kai Sheng</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Three-dimensional (3D) convolution with 3D batch normalization</title><date>2022-08-16</date><risdate>2022</risdate><abstract>A method of classifying three-dimensional (3D) data includes receiving three-dimensional (3D) data and processing the 3D data using a neural network that includes a plurality of subnetworks arranged in a sequence and the data is processed through each of the subnetworks. Each of the subnetworks is configured to receive an output generated by a preceding subnetwork in the sequence, process the output through a plurality of parallel 3D convolution layer paths of varying convolution volume, process the output through a parallel pooling path, and concatenate output of the 3D convolution layer paths and the pooling path to generate an output representation from each of the subnetworks. Following processing the data through the subnetworks, the method includes processing the output of a last one of the subnetworks in the sequence through a vertical pooling layer to generate an output and classifying the received 3D data based upon the generated output.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US11416747B2
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Three-dimensional (3D) convolution with 3D batch normalization
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T17%3A42%3A07IST&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=Socher,%20Richard&rft.date=2022-08-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11416747B2%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