Adaptive neural network management system
A method and computer system for managing a neural network. Data is sent into an input layer in a portion of layers of nodes in the neural network. The data moves on an encode path through the portion such that an output layer in the portion outputs encoded data. The encoded data is sent into the ou...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| 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 | Aimone, James Bradley Draelos, Timothy J |
| description | A method and computer system for managing a neural network. Data is sent into an input layer in a portion of layers of nodes in the neural network. The data moves on an encode path through the portion such that an output layer in the portion outputs encoded data. The encoded data is sent into the output layer on a decode path through the portion back to the input layer to obtain a reconstruction of the data by the input layer. A determination is made as to whether an undesired amount of error has occurred in the output layer based on the data sent into the input layer and the reconstruction of the data. A number of new nodes is added to the output layer when a determination is present that the undesired amount of the error occurred, enabling reducing the error using the number of the new nodes. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US10891540B2</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US10891540B2</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US10891540B23</originalsourceid><addsrcrecordid>eNrjZNB0TEksKMksS1XISy0tSswBUiXl-UXZCrmJeYnpqbmpeSUKxZXFJam5PAysaYk5xam8UJqbQdHNNcTZQze1ID8-tbggMTkVqDc-NNjQwMLS0NTEwMnImBg1AC5pKT0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Adaptive neural network management system</title><source>esp@cenet</source><creator>Aimone, James Bradley ; Draelos, Timothy J</creator><creatorcontrib>Aimone, James Bradley ; Draelos, Timothy J</creatorcontrib><description>A method and computer system for managing a neural network. Data is sent into an input layer in a portion of layers of nodes in the neural network. The data moves on an encode path through the portion such that an output layer in the portion outputs encoded data. The encoded data is sent into the output layer on a decode path through the portion back to the input layer to obtain a reconstruction of the data by the input layer. A determination is made as to whether an undesired amount of error has occurred in the output layer based on the data sent into the input layer and the reconstruction of the data. A number of new nodes is added to the output layer when a determination is present that the undesired amount of the error occurred, enabling reducing the error using the number of the new nodes.</description><language>eng</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&date=20210112&DB=EPODOC&CC=US&NR=10891540B2$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210112&DB=EPODOC&CC=US&NR=10891540B2$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Aimone, James Bradley</creatorcontrib><creatorcontrib>Draelos, Timothy J</creatorcontrib><title>Adaptive neural network management system</title><description>A method and computer system for managing a neural network. Data is sent into an input layer in a portion of layers of nodes in the neural network. The data moves on an encode path through the portion such that an output layer in the portion outputs encoded data. The encoded data is sent into the output layer on a decode path through the portion back to the input layer to obtain a reconstruction of the data by the input layer. A determination is made as to whether an undesired amount of error has occurred in the output layer based on the data sent into the input layer and the reconstruction of the data. A number of new nodes is added to the output layer when a determination is present that the undesired amount of the error occurred, enabling reducing the error using the number of the new nodes.</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>eNrjZNB0TEksKMksS1XISy0tSswBUiXl-UXZCrmJeYnpqbmpeSUKxZXFJam5PAysaYk5xam8UJqbQdHNNcTZQze1ID8-tbggMTkVqDc-NNjQwMLS0NTEwMnImBg1AC5pKT0</recordid><startdate>20210112</startdate><enddate>20210112</enddate><creator>Aimone, James Bradley</creator><creator>Draelos, Timothy J</creator><scope>EVB</scope></search><sort><creationdate>20210112</creationdate><title>Adaptive neural network management system</title><author>Aimone, James Bradley ; Draelos, Timothy J</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US10891540B23</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</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>Aimone, James Bradley</creatorcontrib><creatorcontrib>Draelos, Timothy J</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Aimone, James Bradley</au><au>Draelos, Timothy J</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Adaptive neural network management system</title><date>2021-01-12</date><risdate>2021</risdate><abstract>A method and computer system for managing a neural network. Data is sent into an input layer in a portion of layers of nodes in the neural network. The data moves on an encode path through the portion such that an output layer in the portion outputs encoded data. The encoded data is sent into the output layer on a decode path through the portion back to the input layer to obtain a reconstruction of the data by the input layer. A determination is made as to whether an undesired amount of error has occurred in the output layer based on the data sent into the input layer and the reconstruction of the data. A number of new nodes is added to the output layer when a determination is present that the undesired amount of the error occurred, enabling reducing the error using the number of the new nodes.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US10891540B2 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Adaptive neural network management system |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T03%3A12%3A15IST&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=Aimone,%20James%20Bradley&rft.date=2021-01-12&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS10891540B2%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 |