Quality monitoring and hidden quantization in artificial neural network computations

Systems and methods for quality monitoring and hidden quantization in artificial neural network (ANN) computations are provided. An example method may include receiving a description of an ANN and input data associated with the ANN, performing, based on a quantization scheme, quantization of the ANN...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Larzul, Ludovic, Dumoulin, Frederic
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 Larzul, Ludovic
Dumoulin, Frederic
description Systems and methods for quality monitoring and hidden quantization in artificial neural network (ANN) computations are provided. An example method may include receiving a description of an ANN and input data associated with the ANN, performing, based on a quantization scheme, quantization of the ANN to obtain a quantized ANN, performing, based on the set of input data, ANN computations of the quantized ANN to obtain a result of the ANN computation for the input data, while performing the ANN computations, monitoring, a measure of quality of the ANN computations of the quantized ANN, determining that the measure of quality does not satisfy quality requirements, and in response to the determination, informing a user of an external system of the measure of quality, and adjusting, based on the measure of quality, the quantization scheme to be used in the ANN computations for further input data.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US11625583B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US11625583B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US11625583B23</originalsourceid><addsrcrecordid>eNqNyzEOwjAMQNEsDAi4gzkAQ1sVMYNArIgyV1bigkXqhNQRgtODKg7A9Jf3p6Y5ZfSsL-iDsIbEcgUUBzd2jgQeGUX5jcpBgAUwKXdsGT0I5TRGnyHdwYY-Zh3hMDeTDv1Ai19nZnnYN7vjimJoaYho6bu1l3NRrMu63lTbsvrHfAArtjoo</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Quality monitoring and hidden quantization in artificial neural network computations</title><source>esp@cenet</source><creator>Larzul, Ludovic ; Dumoulin, Frederic</creator><creatorcontrib>Larzul, Ludovic ; Dumoulin, Frederic</creatorcontrib><description>Systems and methods for quality monitoring and hidden quantization in artificial neural network (ANN) computations are provided. An example method may include receiving a description of an ANN and input data associated with the ANN, performing, based on a quantization scheme, quantization of the ANN to obtain a quantized ANN, performing, based on the set of input data, ANN computations of the quantized ANN to obtain a result of the ANN computation for the input data, while performing the ANN computations, monitoring, a measure of quality of the ANN computations of the quantized ANN, determining that the measure of quality does not satisfy quality requirements, and in response to the determination, informing a user of an external system of the measure of quality, and adjusting, based on the measure of quality, the quantization scheme to be used in the ANN computations for further input data.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2023</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=20230411&amp;DB=EPODOC&amp;CC=US&amp;NR=11625583B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,781,886,25568,76551</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230411&amp;DB=EPODOC&amp;CC=US&amp;NR=11625583B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Larzul, Ludovic</creatorcontrib><creatorcontrib>Dumoulin, Frederic</creatorcontrib><title>Quality monitoring and hidden quantization in artificial neural network computations</title><description>Systems and methods for quality monitoring and hidden quantization in artificial neural network (ANN) computations are provided. An example method may include receiving a description of an ANN and input data associated with the ANN, performing, based on a quantization scheme, quantization of the ANN to obtain a quantized ANN, performing, based on the set of input data, ANN computations of the quantized ANN to obtain a result of the ANN computation for the input data, while performing the ANN computations, monitoring, a measure of quality of the ANN computations of the quantized ANN, determining that the measure of quality does not satisfy quality requirements, and in response to the determination, informing a user of an external system of the measure of quality, and adjusting, based on the measure of quality, the quantization scheme to be used in the ANN computations for further input data.</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>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyzEOwjAMQNEsDAi4gzkAQ1sVMYNArIgyV1bigkXqhNQRgtODKg7A9Jf3p6Y5ZfSsL-iDsIbEcgUUBzd2jgQeGUX5jcpBgAUwKXdsGT0I5TRGnyHdwYY-Zh3hMDeTDv1Ai19nZnnYN7vjimJoaYho6bu1l3NRrMu63lTbsvrHfAArtjoo</recordid><startdate>20230411</startdate><enddate>20230411</enddate><creator>Larzul, Ludovic</creator><creator>Dumoulin, Frederic</creator><scope>EVB</scope></search><sort><creationdate>20230411</creationdate><title>Quality monitoring and hidden quantization in artificial neural network computations</title><author>Larzul, Ludovic ; Dumoulin, Frederic</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US11625583B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2023</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Larzul, Ludovic</creatorcontrib><creatorcontrib>Dumoulin, Frederic</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Larzul, Ludovic</au><au>Dumoulin, Frederic</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Quality monitoring and hidden quantization in artificial neural network computations</title><date>2023-04-11</date><risdate>2023</risdate><abstract>Systems and methods for quality monitoring and hidden quantization in artificial neural network (ANN) computations are provided. An example method may include receiving a description of an ANN and input data associated with the ANN, performing, based on a quantization scheme, quantization of the ANN to obtain a quantized ANN, performing, based on the set of input data, ANN computations of the quantized ANN to obtain a result of the ANN computation for the input data, while performing the ANN computations, monitoring, a measure of quality of the ANN computations of the quantized ANN, determining that the measure of quality does not satisfy quality requirements, and in response to the determination, informing a user of an external system of the measure of quality, and adjusting, based on the measure of quality, the quantization scheme to be used in the ANN computations for further input data.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US11625583B2
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Quality monitoring and hidden quantization in artificial neural network computations
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-16T21%3A23%3A49IST&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=Larzul,%20Ludovic&rft.date=2023-04-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS11625583B2%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