AUTOMATIC THRESHOLDS FOR NEURAL NETWORK PRUNING AND RETRAINING

An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	SHIM, Eunsoo, OVSIANNIKOV, Ilia, BROTHERS, John Wakefield, JI, Zhengping
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	SHIM, Eunsoo OVSIANNIKOV, Ilia BROTHERS, John Wakefield JI, Zhengping
description	An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2020410357A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2020410357A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2020410357A13</originalsourceid><addsrcrecordid>eNrjZLBzDA3x93UM8XRWCPEIcg328PdxCVZw8w9S8HMNDXL0AVIh4f5B3goBQaF-nn7uCo5-LgpBriFBjp4gLg8Da1piTnEqL5TmZlB2cw1x9tBNLciPTy0uSExOzUstiQ8NNjIwMjAxNDA2NXc0NCZOFQArHStR</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>AUTOMATIC THRESHOLDS FOR NEURAL NETWORK PRUNING AND RETRAINING</title><source>esp@cenet</source><creator>SHIM, Eunsoo ; OVSIANNIKOV, Ilia ; BROTHERS, John Wakefield ; JI, Zhengping</creator><creatorcontrib>SHIM, Eunsoo ; OVSIANNIKOV, Ilia ; BROTHERS, John Wakefield ; JI, Zhengping</creatorcontrib><description>An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2020</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=20201231&DB=EPODOC&CC=US&NR=2020410357A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20201231&DB=EPODOC&CC=US&NR=2020410357A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SHIM, Eunsoo</creatorcontrib><creatorcontrib>OVSIANNIKOV, Ilia</creatorcontrib><creatorcontrib>BROTHERS, John Wakefield</creatorcontrib><creatorcontrib>JI, Zhengping</creatorcontrib><title>AUTOMATIC THRESHOLDS FOR NEURAL NETWORK PRUNING AND RETRAINING</title><description>An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.</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>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLBzDA3x93UM8XRWCPEIcg328PdxCVZw8w9S8HMNDXL0AVIh4f5B3goBQaF-nn7uCo5-LgpBriFBjp4gLg8Da1piTnEqL5TmZlB2cw1x9tBNLciPTy0uSExOzUstiQ8NNjIwMjAxNDA2NXc0NCZOFQArHStR</recordid><startdate>20201231</startdate><enddate>20201231</enddate><creator>SHIM, Eunsoo</creator><creator>OVSIANNIKOV, Ilia</creator><creator>BROTHERS, John Wakefield</creator><creator>JI, Zhengping</creator><scope>EVB</scope></search><sort><creationdate>20201231</creationdate><title>AUTOMATIC THRESHOLDS FOR NEURAL NETWORK PRUNING AND RETRAINING</title><author>SHIM, Eunsoo ; OVSIANNIKOV, Ilia ; BROTHERS, John Wakefield ; JI, Zhengping</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2020410357A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2020</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>SHIM, Eunsoo</creatorcontrib><creatorcontrib>OVSIANNIKOV, Ilia</creatorcontrib><creatorcontrib>BROTHERS, John Wakefield</creatorcontrib><creatorcontrib>JI, Zhengping</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SHIM, Eunsoo</au><au>OVSIANNIKOV, Ilia</au><au>BROTHERS, John Wakefield</au><au>JI, Zhengping</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>AUTOMATIC THRESHOLDS FOR NEURAL NETWORK PRUNING AND RETRAINING</title><date>2020-12-31</date><risdate>2020</risdate><abstract>An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2020410357A1
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
title	AUTOMATIC THRESHOLDS FOR NEURAL NETWORK PRUNING AND RETRAINING
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T07%3A13%3A41IST&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=SHIM,%20Eunsoo&rft.date=2020-12-31&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2020410357A1%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