PRE-PROCESSING FOR DEEP NEURAL NETWORK COMPILATION USING GRAPH NEURAL NETWORKS
A processor-implemented method of pre-processing for deep neural network compilation comprising receiving a representation of an artificial neural network (ANN) model. The ANN includes multiple nodes coupled by edges. Position information is determined for each node of the ANN. An operator embedding...
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 | BHAMIDIPATI, Anusha V.S UPRETI, Himanshu GATTUPALLI, Venkata Subba Dheeraj BISWAS, Prasanna Ashish GUPTA, Anuj SHARMA, Piyush BADDI, Vinayak Narayan SHARMA, Mohit |
| description | A processor-implemented method of pre-processing for deep neural network compilation comprising receiving a representation of an artificial neural network (ANN) model. The ANN includes multiple nodes coupled by edges. Position information is determined for each node of the ANN. An operator embedding is generated to represent operators of the ANN model in an embedding space based on the position information. A graph neural network (GNN) processes the operator embedding to generate a graph embedding corresponding to the ANN model according to a learned distance metric and based on the position information. The GNN determines a set of hyperparameters for the ANN model based on the graph embedding. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024412035A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024412035A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024412035A13</originalsourceid><addsrcrecordid>eNrjZPALCHLVDQjyd3YNDvb0c1dw8w9ScHF1DVDwcw0NcvQBUiHh_kHeCs7-vgGePo4hnv5-CqFgle5BjgEeaMqCeRhY0xJzilN5oTQ3g7Kba4izh25qQX58anFBYnJqXmpJfGiwkYGRiYmhkYGxqaOhMXGqAPkzL7k</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>PRE-PROCESSING FOR DEEP NEURAL NETWORK COMPILATION USING GRAPH NEURAL NETWORKS</title><source>esp@cenet</source><creator>BHAMIDIPATI, Anusha V.S ; UPRETI, Himanshu ; GATTUPALLI, Venkata Subba Dheeraj ; BISWAS, Prasanna Ashish ; GUPTA, Anuj ; SHARMA, Piyush ; BADDI, Vinayak Narayan ; SHARMA, Mohit</creator><creatorcontrib>BHAMIDIPATI, Anusha V.S ; UPRETI, Himanshu ; GATTUPALLI, Venkata Subba Dheeraj ; BISWAS, Prasanna Ashish ; GUPTA, Anuj ; SHARMA, Piyush ; BADDI, Vinayak Narayan ; SHARMA, Mohit</creatorcontrib><description>A processor-implemented method of pre-processing for deep neural network compilation comprising receiving a representation of an artificial neural network (ANN) model. The ANN includes multiple nodes coupled by edges. Position information is determined for each node of the ANN. An operator embedding is generated to represent operators of the ANN model in an embedding space based on the position information. A graph neural network (GNN) processes the operator embedding to generate a graph embedding corresponding to the ANN model according to a learned distance metric and based on the position information. The GNN determines a set of hyperparameters for the ANN model based on the graph embedding.</description><language>eng</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&date=20241212&DB=EPODOC&CC=US&NR=2024412035A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20241212&DB=EPODOC&CC=US&NR=2024412035A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>BHAMIDIPATI, Anusha V.S</creatorcontrib><creatorcontrib>UPRETI, Himanshu</creatorcontrib><creatorcontrib>GATTUPALLI, Venkata Subba Dheeraj</creatorcontrib><creatorcontrib>BISWAS, Prasanna Ashish</creatorcontrib><creatorcontrib>GUPTA, Anuj</creatorcontrib><creatorcontrib>SHARMA, Piyush</creatorcontrib><creatorcontrib>BADDI, Vinayak Narayan</creatorcontrib><creatorcontrib>SHARMA, Mohit</creatorcontrib><title>PRE-PROCESSING FOR DEEP NEURAL NETWORK COMPILATION USING GRAPH NEURAL NETWORKS</title><description>A processor-implemented method of pre-processing for deep neural network compilation comprising receiving a representation of an artificial neural network (ANN) model. The ANN includes multiple nodes coupled by edges. Position information is determined for each node of the ANN. An operator embedding is generated to represent operators of the ANN model in an embedding space based on the position information. A graph neural network (GNN) processes the operator embedding to generate a graph embedding corresponding to the ANN model according to a learned distance metric and based on the position information. The GNN determines a set of hyperparameters for the ANN model based on the graph embedding.</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>eNrjZPALCHLVDQjyd3YNDvb0c1dw8w9ScHF1DVDwcw0NcvQBUiHh_kHeCs7-vgGePo4hnv5-CqFgle5BjgEeaMqCeRhY0xJzilN5oTQ3g7Kba4izh25qQX58anFBYnJqXmpJfGiwkYGRiYmhkYGxqaOhMXGqAPkzL7k</recordid><startdate>20241212</startdate><enddate>20241212</enddate><creator>BHAMIDIPATI, Anusha V.S</creator><creator>UPRETI, Himanshu</creator><creator>GATTUPALLI, Venkata Subba Dheeraj</creator><creator>BISWAS, Prasanna Ashish</creator><creator>GUPTA, Anuj</creator><creator>SHARMA, Piyush</creator><creator>BADDI, Vinayak Narayan</creator><creator>SHARMA, Mohit</creator><scope>EVB</scope></search><sort><creationdate>20241212</creationdate><title>PRE-PROCESSING FOR DEEP NEURAL NETWORK COMPILATION USING GRAPH NEURAL NETWORKS</title><author>BHAMIDIPATI, Anusha V.S ; UPRETI, Himanshu ; GATTUPALLI, Venkata Subba Dheeraj ; BISWAS, Prasanna Ashish ; GUPTA, Anuj ; SHARMA, Piyush ; BADDI, Vinayak Narayan ; SHARMA, Mohit</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024412035A13</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>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>BHAMIDIPATI, Anusha V.S</creatorcontrib><creatorcontrib>UPRETI, Himanshu</creatorcontrib><creatorcontrib>GATTUPALLI, Venkata Subba Dheeraj</creatorcontrib><creatorcontrib>BISWAS, Prasanna Ashish</creatorcontrib><creatorcontrib>GUPTA, Anuj</creatorcontrib><creatorcontrib>SHARMA, Piyush</creatorcontrib><creatorcontrib>BADDI, Vinayak Narayan</creatorcontrib><creatorcontrib>SHARMA, Mohit</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>BHAMIDIPATI, Anusha V.S</au><au>UPRETI, Himanshu</au><au>GATTUPALLI, Venkata Subba Dheeraj</au><au>BISWAS, Prasanna Ashish</au><au>GUPTA, Anuj</au><au>SHARMA, Piyush</au><au>BADDI, Vinayak Narayan</au><au>SHARMA, Mohit</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>PRE-PROCESSING FOR DEEP NEURAL NETWORK COMPILATION USING GRAPH NEURAL NETWORKS</title><date>2024-12-12</date><risdate>2024</risdate><abstract>A processor-implemented method of pre-processing for deep neural network compilation comprising receiving a representation of an artificial neural network (ANN) model. The ANN includes multiple nodes coupled by edges. Position information is determined for each node of the ANN. An operator embedding is generated to represent operators of the ANN model in an embedding space based on the position information. A graph neural network (GNN) processes the operator embedding to generate a graph embedding corresponding to the ANN model according to a learned distance metric and based on the position information. The GNN determines a set of hyperparameters for the ANN model based on the graph embedding.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2024412035A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | PRE-PROCESSING FOR DEEP NEURAL NETWORK COMPILATION USING GRAPH NEURAL NETWORKS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-04T16%3A20%3A29IST&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=BHAMIDIPATI,%20Anusha%20V.S&rft.date=2024-12-12&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024412035A1%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 |