LEARNING WITH MOMENT ESTIMATION USING DIFFERENT TIME CONSTANTS

LEARNING WITH MOMENT ESTIMATION USING DIFFERENT TIME CONSTANTS

A technique for training a model includes obtaining a training example for a model having model parameters stored on one or more computer readable storage mediums operably coupled to the hardware processor. The training example includes an outcome and features to explain the outcome. A gradient is c...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Morimura, Tetsuro
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 Morimura, Tetsuro
description A technique for training a model includes obtaining a training example for a model having model parameters stored on one or more computer readable storage mediums operably coupled to the hardware processor. The training example includes an outcome and features to explain the outcome. A gradient is calculated with respect to the model parameters of the model using the training example. Two estimates of a moment of the gradient with two different time constants are computed for the same type of the moment using the gradient. Using a hardware processor, the model parameters of the model are updated using the two estimates of the moment with the two different time constants to reduce errors while calculating the at least two estimates of the moment of the gradient.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2023252357A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2023252357A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2023252357A13</originalsourceid><addsrcrecordid>eNrjZLDzcXUM8vP0c1cI9wzxUPD193X1C1FwDQ7x9HUM8fT3UwgNBkm6eLq5uQaBpIASrgrO_n7BIY5-IcE8DKxpiTnFqbxQmptB2c01xNlDN7UgPz61uCAxOTUvtSQ-NNjIwMjYyNTI2NTc0dCYOFUAJKwrWQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>LEARNING WITH MOMENT ESTIMATION USING DIFFERENT TIME CONSTANTS</title><source>esp@cenet</source><creator>Morimura, Tetsuro</creator><creatorcontrib>Morimura, Tetsuro</creatorcontrib><description>A technique for training a model includes obtaining a training example for a model having model parameters stored on one or more computer readable storage mediums operably coupled to the hardware processor. The training example includes an outcome and features to explain the outcome. A gradient is calculated with respect to the model parameters of the model using the training example. Two estimates of a moment of the gradient with two different time constants are computed for the same type of the moment using the gradient. Using a hardware processor, the model parameters of the model are updated using the two estimates of the moment with the two different time constants to reduce errors while calculating the at least two estimates of the moment of the gradient.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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=20230810&amp;DB=EPODOC&amp;CC=US&amp;NR=2023252357A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230810&amp;DB=EPODOC&amp;CC=US&amp;NR=2023252357A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Morimura, Tetsuro</creatorcontrib><title>LEARNING WITH MOMENT ESTIMATION USING DIFFERENT TIME CONSTANTS</title><description>A technique for training a model includes obtaining a training example for a model having model parameters stored on one or more computer readable storage mediums operably coupled to the hardware processor. The training example includes an outcome and features to explain the outcome. A gradient is calculated with respect to the model parameters of the model using the training example. Two estimates of a moment of the gradient with two different time constants are computed for the same type of the moment using the gradient. Using a hardware processor, the model parameters of the model are updated using the two estimates of the moment with the two different time constants to reduce errors while calculating the at least two estimates of the moment of the gradient.</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>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLDzcXUM8vP0c1cI9wzxUPD193X1C1FwDQ7x9HUM8fT3UwgNBkm6eLq5uQaBpIASrgrO_n7BIY5-IcE8DKxpiTnFqbxQmptB2c01xNlDN7UgPz61uCAxOTUvtSQ-NNjIwMjYyNTI2NTc0dCYOFUAJKwrWQ</recordid><startdate>20230810</startdate><enddate>20230810</enddate><creator>Morimura, Tetsuro</creator><scope>EVB</scope></search><sort><creationdate>20230810</creationdate><title>LEARNING WITH MOMENT ESTIMATION USING DIFFERENT TIME CONSTANTS</title><author>Morimura, Tetsuro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2023252357A13</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Morimura, Tetsuro</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Morimura, Tetsuro</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>LEARNING WITH MOMENT ESTIMATION USING DIFFERENT TIME CONSTANTS</title><date>2023-08-10</date><risdate>2023</risdate><abstract>A technique for training a model includes obtaining a training example for a model having model parameters stored on one or more computer readable storage mediums operably coupled to the hardware processor. The training example includes an outcome and features to explain the outcome. A gradient is calculated with respect to the model parameters of the model using the training example. Two estimates of a moment of the gradient with two different time constants are computed for the same type of the moment using the gradient. Using a hardware processor, the model parameters of the model are updated using the two estimates of the moment with the two different time constants to reduce errors while calculating the at least two estimates of the moment of the gradient.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2023252357A1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title LEARNING WITH MOMENT ESTIMATION USING DIFFERENT TIME CONSTANTS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T15%3A34%3A59IST&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=Morimura,%20Tetsuro&rft.date=2023-08-10&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2023252357A1%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