Structure learning in convolutional neural networks

The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Malisiewicz, Tomasz J, Detone, Daniel, Rajendran, Srivignesh, Lee, Douglas Bertram, Rabinovich, Andrew, Badrinarayanan, Vijay
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING 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	Malisiewicz, Tomasz J Detone, Daniel Rajendran, Srivignesh Lee, Douglas Bertram Rabinovich, Andrew Badrinarayanan, Vijay
description	The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_AU2017230184A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>AU2017230184A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_AU2017230184A13</originalsourceid><addsrcrecordid>eNrjZDAOLikqTS4pLUpVyElNLMrLzEtXyMxTSM7PK8vPKS3JzM9LzFHISy0tAlMl5flF2cU8DKxpiTnFqbxQmptB2c01xNlDN7UgPz61uCAxORWoNN4x1MjA0NzI2MDQwsTR0Jg4VQANCC4L</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Structure learning in convolutional neural networks</title><source>esp@cenet</source><creator>Malisiewicz, Tomasz J ; Detone, Daniel ; Rajendran, Srivignesh ; Lee, Douglas Bertram ; Rabinovich, Andrew ; Badrinarayanan, Vijay</creator><creatorcontrib>Malisiewicz, Tomasz J ; Detone, Daniel ; Rajendran, Srivignesh ; Lee, Douglas Bertram ; Rabinovich, Andrew ; Badrinarayanan, Vijay</creatorcontrib><description>The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2018</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=20180906&DB=EPODOC&CC=AU&NR=2017230184A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20180906&DB=EPODOC&CC=AU&NR=2017230184A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Malisiewicz, Tomasz J</creatorcontrib><creatorcontrib>Detone, Daniel</creatorcontrib><creatorcontrib>Rajendran, Srivignesh</creatorcontrib><creatorcontrib>Lee, Douglas Bertram</creatorcontrib><creatorcontrib>Rabinovich, Andrew</creatorcontrib><creatorcontrib>Badrinarayanan, Vijay</creatorcontrib><title>Structure learning in convolutional neural networks</title><description>The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.</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>2018</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDAOLikqTS4pLUpVyElNLMrLzEtXyMxTSM7PK8vPKS3JzM9LzFHISy0tAlMl5flF2cU8DKxpiTnFqbxQmptB2c01xNlDN7UgPz61uCAxORWoNN4x1MjA0NzI2MDQwsTR0Jg4VQANCC4L</recordid><startdate>20180906</startdate><enddate>20180906</enddate><creator>Malisiewicz, Tomasz J</creator><creator>Detone, Daniel</creator><creator>Rajendran, Srivignesh</creator><creator>Lee, Douglas Bertram</creator><creator>Rabinovich, Andrew</creator><creator>Badrinarayanan, Vijay</creator><scope>EVB</scope></search><sort><creationdate>20180906</creationdate><title>Structure learning in convolutional neural networks</title><author>Malisiewicz, Tomasz J ; Detone, Daniel ; Rajendran, Srivignesh ; Lee, Douglas Bertram ; Rabinovich, Andrew ; Badrinarayanan, Vijay</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_AU2017230184A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2018</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>Malisiewicz, Tomasz J</creatorcontrib><creatorcontrib>Detone, Daniel</creatorcontrib><creatorcontrib>Rajendran, Srivignesh</creatorcontrib><creatorcontrib>Lee, Douglas Bertram</creatorcontrib><creatorcontrib>Rabinovich, Andrew</creatorcontrib><creatorcontrib>Badrinarayanan, Vijay</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Malisiewicz, Tomasz J</au><au>Detone, Daniel</au><au>Rajendran, Srivignesh</au><au>Lee, Douglas Bertram</au><au>Rabinovich, Andrew</au><au>Badrinarayanan, Vijay</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Structure learning in convolutional neural networks</title><date>2018-09-06</date><risdate>2018</risdate><abstract>The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_AU2017230184A1
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
title	Structure learning in convolutional neural networks
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T18%3A49%3A38IST&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=Malisiewicz,%20Tomasz%20J&rft.date=2018-09-06&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EAU2017230184A1%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