NEURALT NETVÆRK OG FREMGANGSMÅDER TIL TRÆNING AF NEURALT NETVÆRK

NEURALT NETVÆRK OG FREMGANGSMÅDER TIL TRÆNING AF NEURALT NETVÆRK

A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects on...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: PESCIANSCHI, Dmitri
Format: Patent
Sprache:dan
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 PESCIANSCHI, Dmitri
description A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects one or more corrective weights in correlation with the input value. The network also includes neurons. Each neuron has an output connected with at least one of the inputs via one synapse and generates a neuron sum by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a weight correction calculator that receives a desired output signal, determines a deviation of the neuron sum from the desired output signal value, and modifies respective corrective weights using the determined deviation. Adding up the modified corrective weights to determine the neuron sum minimizes the subject deviation for training the neural network.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_DK3114540TT3</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>DK3114540TT3</sourcerecordid><originalsourceid>FETCH-epo_espacenet_DK3114540TT33</originalsourceid><addsrcrecordid>eNrjZHDxcw0NcvQJUfBzDQk73BbkreDvruAW5Orr7ujnHux7uNXFNUghxNNHISTocJufp5-7gqObAroeHgbWtMSc4lReKM3NoOjmGuLsoZtakB-fWlyQmJyal1oS7-JtbGhoYmpiEBJibEyMGgDM3S8m</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>NEURALT NETVÆRK OG FREMGANGSMÅDER TIL TRÆNING AF NEURALT NETVÆRK</title><source>esp@cenet</source><creator>PESCIANSCHI, Dmitri</creator><creatorcontrib>PESCIANSCHI, Dmitri</creatorcontrib><description>A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects one or more corrective weights in correlation with the input value. The network also includes neurons. Each neuron has an output connected with at least one of the inputs via one synapse and generates a neuron sum by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a weight correction calculator that receives a desired output signal, determines a deviation of the neuron sum from the desired output signal value, and modifies respective corrective weights using the determined deviation. Adding up the modified corrective weights to determine the neuron sum minimizes the subject deviation for training the neural network.</description><language>dan</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2021</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=20210419&amp;DB=EPODOC&amp;CC=DK&amp;NR=3114540T3$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20210419&amp;DB=EPODOC&amp;CC=DK&amp;NR=3114540T3$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>PESCIANSCHI, Dmitri</creatorcontrib><title>NEURALT NETVÆRK OG FREMGANGSMÅDER TIL TRÆNING AF NEURALT NETVÆRK</title><description>A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects one or more corrective weights in correlation with the input value. The network also includes neurons. Each neuron has an output connected with at least one of the inputs via one synapse and generates a neuron sum by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a weight correction calculator that receives a desired output signal, determines a deviation of the neuron sum from the desired output signal value, and modifies respective corrective weights using the determined deviation. Adding up the modified corrective weights to determine the neuron sum minimizes the subject deviation for training the neural network.</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>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHDxcw0NcvQJUfBzDQk73BbkreDvruAW5Orr7ujnHux7uNXFNUghxNNHISTocJufp5-7gqObAroeHgbWtMSc4lReKM3NoOjmGuLsoZtakB-fWlyQmJyal1oS7-JtbGhoYmpiEBJibEyMGgDM3S8m</recordid><startdate>20210419</startdate><enddate>20210419</enddate><creator>PESCIANSCHI, Dmitri</creator><scope>EVB</scope></search><sort><creationdate>20210419</creationdate><title>NEURALT NETVÆRK OG FREMGANGSMÅDER TIL TRÆNING AF NEURALT NETVÆRK</title><author>PESCIANSCHI, Dmitri</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_DK3114540TT33</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>dan</language><creationdate>2021</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>PESCIANSCHI, Dmitri</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>PESCIANSCHI, Dmitri</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>NEURALT NETVÆRK OG FREMGANGSMÅDER TIL TRÆNING AF NEURALT NETVÆRK</title><date>2021-04-19</date><risdate>2021</risdate><abstract>A neural network includes a plurality of inputs for receiving input signals, and synapses connected to the inputs and having corrective weights. The network additionally includes distributors. Each distributor is connected to one of the inputs for receiving the respective input signal and selects one or more corrective weights in correlation with the input value. The network also includes neurons. Each neuron has an output connected with at least one of the inputs via one synapse and generates a neuron sum by summing corrective weights selected from each synapse connected to the respective neuron. Furthermore, the network includes a weight correction calculator that receives a desired output signal, determines a deviation of the neuron sum from the desired output signal value, and modifies respective corrective weights using the determined deviation. Adding up the modified corrective weights to determine the neuron sum minimizes the subject deviation for training the neural network.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language dan
recordid cdi_epo_espacenet_DK3114540TT3
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title NEURALT NETVÆRK OG FREMGANGSMÅDER TIL TRÆNING AF NEURALT NETVÆRK
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T14%3A33%3A53IST&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=PESCIANSCHI,%20Dmitri&rft.date=2021-04-19&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EDK3114540TT3%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