FLEXIBLE SCHEMA TABLES
In an artificial neural network, integrality refers to the degree to which a neuron generates, for a given set of inputs, outputs that are near the border of the output range of a neuron. From each neural network of a pool of trained neural networks, a group of neurons with a higher integrality is s...
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 | Iyer, Chandrasekharan Chaudhry, Atif Hammerschmidt, Beda Christoph |
| description | In an artificial neural network, integrality refers to the degree to which a neuron generates, for a given set of inputs, outputs that are near the border of the output range of a neuron. From each neural network of a pool of trained neural networks, a group of neurons with a higher integrality is selected to form a neural network tunnel ("tunnel"). The tunnel must include all input neurons and output neurons from the neural network, and some of the hidden neurons. Tunnels generated from each neural network in a pool are merged to form another neural network. The new network may then be trained. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2021224287A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2021224287A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2021224287A13</originalsourceid><addsrcrecordid>eNrjZBBz83GN8HTycVUIdvZw9XVUCHEEcoJ5GFjTEnOKU3mhNDeDsptriLOHbmpBfnxqcUFicmpeakl8aLCRgZGhkZGJkYW5o6ExcaoAH7gf5A</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>FLEXIBLE SCHEMA TABLES</title><source>esp@cenet</source><creator>Iyer, Chandrasekharan ; Chaudhry, Atif ; Hammerschmidt, Beda Christoph</creator><creatorcontrib>Iyer, Chandrasekharan ; Chaudhry, Atif ; Hammerschmidt, Beda Christoph</creatorcontrib><description>In an artificial neural network, integrality refers to the degree to which a neuron generates, for a given set of inputs, outputs that are near the border of the output range of a neuron. From each neural network of a pool of trained neural networks, a group of neurons with a higher integrality is selected to form a neural network tunnel ("tunnel"). The tunnel must include all input neurons and output neurons from the neural network, and some of the hidden neurons. Tunnels generated from each neural network in a pool are merged to form another neural network. The new network may then be trained.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; 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=20210722&DB=EPODOC&CC=US&NR=2021224287A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210722&DB=EPODOC&CC=US&NR=2021224287A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Iyer, Chandrasekharan</creatorcontrib><creatorcontrib>Chaudhry, Atif</creatorcontrib><creatorcontrib>Hammerschmidt, Beda Christoph</creatorcontrib><title>FLEXIBLE SCHEMA TABLES</title><description>In an artificial neural network, integrality refers to the degree to which a neuron generates, for a given set of inputs, outputs that are near the border of the output range of a neuron. From each neural network of a pool of trained neural networks, a group of neurons with a higher integrality is selected to form a neural network tunnel ("tunnel"). The tunnel must include all input neurons and output neurons from the neural network, and some of the hidden neurons. Tunnels generated from each neural network in a pool are merged to form another neural network. The new network may then be trained.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2021</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZBBz83GN8HTycVUIdvZw9XVUCHEEcoJ5GFjTEnOKU3mhNDeDsptriLOHbmpBfnxqcUFicmpeakl8aLCRgZGhkZGJkYW5o6ExcaoAH7gf5A</recordid><startdate>20210722</startdate><enddate>20210722</enddate><creator>Iyer, Chandrasekharan</creator><creator>Chaudhry, Atif</creator><creator>Hammerschmidt, Beda Christoph</creator><scope>EVB</scope></search><sort><creationdate>20210722</creationdate><title>FLEXIBLE SCHEMA TABLES</title><author>Iyer, Chandrasekharan ; Chaudhry, Atif ; Hammerschmidt, Beda Christoph</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2021224287A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2021</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Iyer, Chandrasekharan</creatorcontrib><creatorcontrib>Chaudhry, Atif</creatorcontrib><creatorcontrib>Hammerschmidt, Beda Christoph</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Iyer, Chandrasekharan</au><au>Chaudhry, Atif</au><au>Hammerschmidt, Beda Christoph</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>FLEXIBLE SCHEMA TABLES</title><date>2021-07-22</date><risdate>2021</risdate><abstract>In an artificial neural network, integrality refers to the degree to which a neuron generates, for a given set of inputs, outputs that are near the border of the output range of a neuron. From each neural network of a pool of trained neural networks, a group of neurons with a higher integrality is selected to form a neural network tunnel ("tunnel"). The tunnel must include all input neurons and output neurons from the neural network, and some of the hidden neurons. Tunnels generated from each neural network in a pool are merged to form another neural network. The new network may then be trained.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2021224287A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | FLEXIBLE SCHEMA TABLES |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T13%3A29%3A21IST&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=Iyer,%20Chandrasekharan&rft.date=2021-07-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2021224287A1%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 |