METHOD AND APPARATUS FOR AUTOMATICALLY PRODUCING AN ARTIFICIAL NEURAL NETWORK

METHOD AND APPARATUS FOR AUTOMATICALLY PRODUCING AN ARTIFICIAL NEURAL NETWORK

A method for automatically generating an artificial neural network that encompasses modules and connections that link those modules, successive modules and/or connections being added to a current starting network. Modules and/or connections that are to be added are selected randomly from a predefina...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HUTTER, Frank, METZEN, Jan Hendrik, ELSKEN, Thomas
Format: Patent
Sprache:eng ; fre ; ger
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 HUTTER, Frank
METZEN, Jan Hendrik
ELSKEN, Thomas
description A method for automatically generating an artificial neural network that encompasses modules and connections that link those modules, successive modules and/or connections being added to a current starting network. Modules and/or connections that are to be added are selected randomly from a predefinable plurality of possible modules and connections that can be added. A plurality of possible refinements of the current starting network respectively are generated by adding to the starting network modules and/or connections that are to be added. One of the refinements from the plurality of possible refinements is then selected in order to serve as a current starting network in a subsequent execution of the method.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP3701434B1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP3701434B1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP3701434B13</originalsourceid><addsrcrecordid>eNrjZPD1dQ3x8HdRcPQD4oAAxyDHkNBgBTf_IAXH0BB_X8cQT2dHH59IhYAgf5dQZ08_d6BKBcegEE83T2dPRx8FP9fQIDAVEu4f5M3DwJqWmFOcyguluRkU3FxDnD10Uwvy41OLCxKTU_NSS-JdA4zNDQxNjE2cDI2JUAIAnJkt8g</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>METHOD AND APPARATUS FOR AUTOMATICALLY PRODUCING AN ARTIFICIAL NEURAL NETWORK</title><source>esp@cenet</source><creator>HUTTER, Frank ; METZEN, Jan Hendrik ; ELSKEN, Thomas</creator><creatorcontrib>HUTTER, Frank ; METZEN, Jan Hendrik ; ELSKEN, Thomas</creatorcontrib><description>A method for automatically generating an artificial neural network that encompasses modules and connections that link those modules, successive modules and/or connections being added to a current starting network. Modules and/or connections that are to be added are selected randomly from a predefinable plurality of possible modules and connections that can be added. A plurality of possible refinements of the current starting network respectively are generated by adding to the starting network modules and/or connections that are to be added. One of the refinements from the plurality of possible refinements is then selected in order to serve as a current starting network in a subsequent execution of the method.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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=20241211&amp;DB=EPODOC&amp;CC=EP&amp;NR=3701434B1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25544,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20241211&amp;DB=EPODOC&amp;CC=EP&amp;NR=3701434B1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HUTTER, Frank</creatorcontrib><creatorcontrib>METZEN, Jan Hendrik</creatorcontrib><creatorcontrib>ELSKEN, Thomas</creatorcontrib><title>METHOD AND APPARATUS FOR AUTOMATICALLY PRODUCING AN ARTIFICIAL NEURAL NETWORK</title><description>A method for automatically generating an artificial neural network that encompasses modules and connections that link those modules, successive modules and/or connections being added to a current starting network. Modules and/or connections that are to be added are selected randomly from a predefinable plurality of possible modules and connections that can be added. A plurality of possible refinements of the current starting network respectively are generated by adding to the starting network modules and/or connections that are to be added. One of the refinements from the plurality of possible refinements is then selected in order to serve as a current starting network in a subsequent execution of the method.</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPD1dQ3x8HdRcPQD4oAAxyDHkNBgBTf_IAXH0BB_X8cQT2dHH59IhYAgf5dQZ08_d6BKBcegEE83T2dPRx8FP9fQIDAVEu4f5M3DwJqWmFOcyguluRkU3FxDnD10Uwvy41OLCxKTU_NSS-JdA4zNDQxNjE2cDI2JUAIAnJkt8g</recordid><startdate>20241211</startdate><enddate>20241211</enddate><creator>HUTTER, Frank</creator><creator>METZEN, Jan Hendrik</creator><creator>ELSKEN, Thomas</creator><scope>EVB</scope></search><sort><creationdate>20241211</creationdate><title>METHOD AND APPARATUS FOR AUTOMATICALLY PRODUCING AN ARTIFICIAL NEURAL NETWORK</title><author>HUTTER, Frank ; METZEN, Jan Hendrik ; ELSKEN, Thomas</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP3701434B13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2024</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>HUTTER, Frank</creatorcontrib><creatorcontrib>METZEN, Jan Hendrik</creatorcontrib><creatorcontrib>ELSKEN, Thomas</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HUTTER, Frank</au><au>METZEN, Jan Hendrik</au><au>ELSKEN, Thomas</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>METHOD AND APPARATUS FOR AUTOMATICALLY PRODUCING AN ARTIFICIAL NEURAL NETWORK</title><date>2024-12-11</date><risdate>2024</risdate><abstract>A method for automatically generating an artificial neural network that encompasses modules and connections that link those modules, successive modules and/or connections being added to a current starting network. Modules and/or connections that are to be added are selected randomly from a predefinable plurality of possible modules and connections that can be added. A plurality of possible refinements of the current starting network respectively are generated by adding to the starting network modules and/or connections that are to be added. One of the refinements from the plurality of possible refinements is then selected in order to serve as a current starting network in a subsequent execution of the method.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP3701434B1
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title METHOD AND APPARATUS FOR AUTOMATICALLY PRODUCING AN ARTIFICIAL NEURAL NETWORK
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T16%3A47%3A28IST&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=HUTTER,%20Frank&rft.date=2024-12-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP3701434B1%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