DATA COMPRESSION USING INTEGER NEURAL NETWORKS

DATA COMPRESSION USING INTEGER NEURAL NETWORKS

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Balle, Johannes, Johnston, Nicholas
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 Balle, Johannes
Johnston, Nicholas
description Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the data.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024104786A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024104786A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024104786A13</originalsourceid><addsrcrecordid>eNrjZNBzcQxxVHD29w0Icg0O9vT3UwgN9vRzV_D0C3F1dw1S8HMNDXL0AVIh4f5B3sE8DKxpiTnFqbxQmptB2c01xNlDN7UgPz61uCAxOTUvtSQ-NNjIwMjE0MDE3MLM0dCYOFUAlB4m8Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>DATA COMPRESSION USING INTEGER NEURAL NETWORKS</title><source>esp@cenet</source><creator>Balle, Johannes ; Johnston, Nicholas</creator><creatorcontrib>Balle, Johannes ; Johnston, Nicholas</creatorcontrib><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the data.</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>2024</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=20240328&amp;DB=EPODOC&amp;CC=US&amp;NR=2024104786A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25551,76304</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240328&amp;DB=EPODOC&amp;CC=US&amp;NR=2024104786A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Balle, Johannes</creatorcontrib><creatorcontrib>Johnston, Nicholas</creatorcontrib><title>DATA COMPRESSION USING INTEGER NEURAL NETWORKS</title><description>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the 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>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNBzcQxxVHD29w0Icg0O9vT3UwgN9vRzV_D0C3F1dw1S8HMNDXL0AVIh4f5B3sE8DKxpiTnFqbxQmptB2c01xNlDN7UgPz61uCAxOTUvtSQ-NNjIwMjE0MDE3MLM0dCYOFUAlB4m8Q</recordid><startdate>20240328</startdate><enddate>20240328</enddate><creator>Balle, Johannes</creator><creator>Johnston, Nicholas</creator><scope>EVB</scope></search><sort><creationdate>20240328</creationdate><title>DATA COMPRESSION USING INTEGER NEURAL NETWORKS</title><author>Balle, Johannes ; Johnston, Nicholas</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024104786A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</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>Balle, Johannes</creatorcontrib><creatorcontrib>Johnston, Nicholas</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Balle, Johannes</au><au>Johnston, Nicholas</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>DATA COMPRESSION USING INTEGER NEURAL NETWORKS</title><date>2024-03-28</date><risdate>2024</risdate><abstract>Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reliably performing data compression and data decompression across a wide variety of hardware and software platforms by using integer neural networks. In one aspect, there is provided a method for entropy encoding data which defines a sequence comprising a plurality of components, the method comprising: for each component of the plurality of components: processing an input comprising: (i) a respective integer representation of each of one or more components of the data which precede the component in the sequence, (ii) an integer representation of one or more respective latent variables characterizing the data, or (iii) both, using an integer neural network to generate data defining a probability distribution over the predetermined set of possible code symbols for the component of the data.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2024104786A1
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 DATA COMPRESSION USING INTEGER NEURAL NETWORKS
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T10%3A34%3A10IST&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=Balle,%20Johannes&rft.date=2024-03-28&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024104786A1%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