Image data classification method for online training spiking neural network model along with time
The invention discloses an image data classification method for online training a pulse neural network model along with time. The method comprises the following steps: constructing a pulse neural network model and designing an online method training model along with time; the trained model is used f...
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Patent |
| Sprache: | chi ; 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 | HE DI XIAO MINGQING ZHANG ZONGPENG MENG QINGYAN LIN ZHONGCHEN |
| description | The invention discloses an image data classification method for online training a pulse neural network model along with time. The method comprises the following steps: constructing a pulse neural network model and designing an online method training model along with time; the trained model is used for classifying and recognizing the image data, so that the classification and recognition performance of the image data is effectively improved; wherein the image data comprises computer image data and image visual data of the neuromorphic. Through the method provided by the invention, when the pulse neural network SNN model is trained, the overhead of a training memory can be greatly reduced, the trained model is used for visual tasks such as classification and recognition of computer image data and neuromorphic image visual data, the classification and recognition performance can be improved, the processing delay of a recognition system is reduced, and the recognition efficiency is improved. And an efficient and |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114998659A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114998659A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114998659A3</originalsourceid><addsrcrecordid>eNqNyz0OwjAMhuEsDAi4gzkAQ8WP6IgqECxM7JXVuK3VxK4So16fInEApmd4v2_p8BGxI_BoCE3AnLnlBo1VIJL16qHVBCqBhcASsrB0kEcevgq9E4YZmzQNENVTAAw6p4mtB-NIa7doMWTa_Fy57e36qu47GrWmPGJD87-unkVxKMvz6Vhe9v9sPivZPhU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Image data classification method for online training spiking neural network model along with time</title><source>esp@cenet</source><creator>HE DI ; XIAO MINGQING ; ZHANG ZONGPENG ; MENG QINGYAN ; LIN ZHONGCHEN</creator><creatorcontrib>HE DI ; XIAO MINGQING ; ZHANG ZONGPENG ; MENG QINGYAN ; LIN ZHONGCHEN</creatorcontrib><description>The invention discloses an image data classification method for online training a pulse neural network model along with time. The method comprises the following steps: constructing a pulse neural network model and designing an online method training model along with time; the trained model is used for classifying and recognizing the image data, so that the classification and recognition performance of the image data is effectively improved; wherein the image data comprises computer image data and image visual data of the neuromorphic. Through the method provided by the invention, when the pulse neural network SNN model is trained, the overhead of a training memory can be greatly reduced, the trained model is used for visual tasks such as classification and recognition of computer image data and neuromorphic image visual data, the classification and recognition performance can be improved, the processing delay of a recognition system is reduced, and the recognition efficiency is improved. And an efficient and</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</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=20220902&DB=EPODOC&CC=CN&NR=114998659A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76516</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20220902&DB=EPODOC&CC=CN&NR=114998659A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HE DI</creatorcontrib><creatorcontrib>XIAO MINGQING</creatorcontrib><creatorcontrib>ZHANG ZONGPENG</creatorcontrib><creatorcontrib>MENG QINGYAN</creatorcontrib><creatorcontrib>LIN ZHONGCHEN</creatorcontrib><title>Image data classification method for online training spiking neural network model along with time</title><description>The invention discloses an image data classification method for online training a pulse neural network model along with time. The method comprises the following steps: constructing a pulse neural network model and designing an online method training model along with time; the trained model is used for classifying and recognizing the image data, so that the classification and recognition performance of the image data is effectively improved; wherein the image data comprises computer image data and image visual data of the neuromorphic. Through the method provided by the invention, when the pulse neural network SNN model is trained, the overhead of a training memory can be greatly reduced, the trained model is used for visual tasks such as classification and recognition of computer image data and neuromorphic image visual data, the classification and recognition performance can be improved, the processing delay of a recognition system is reduced, and the recognition efficiency is improved. And an efficient and</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyz0OwjAMhuEsDAi4gzkAQ8WP6IgqECxM7JXVuK3VxK4So16fInEApmd4v2_p8BGxI_BoCE3AnLnlBo1VIJL16qHVBCqBhcASsrB0kEcevgq9E4YZmzQNENVTAAw6p4mtB-NIa7doMWTa_Fy57e36qu47GrWmPGJD87-unkVxKMvz6Vhe9v9sPivZPhU</recordid><startdate>20220902</startdate><enddate>20220902</enddate><creator>HE DI</creator><creator>XIAO MINGQING</creator><creator>ZHANG ZONGPENG</creator><creator>MENG QINGYAN</creator><creator>LIN ZHONGCHEN</creator><scope>EVB</scope></search><sort><creationdate>20220902</creationdate><title>Image data classification method for online training spiking neural network model along with time</title><author>HE DI ; XIAO MINGQING ; ZHANG ZONGPENG ; MENG QINGYAN ; LIN ZHONGCHEN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114998659A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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>HE DI</creatorcontrib><creatorcontrib>XIAO MINGQING</creatorcontrib><creatorcontrib>ZHANG ZONGPENG</creatorcontrib><creatorcontrib>MENG QINGYAN</creatorcontrib><creatorcontrib>LIN ZHONGCHEN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HE DI</au><au>XIAO MINGQING</au><au>ZHANG ZONGPENG</au><au>MENG QINGYAN</au><au>LIN ZHONGCHEN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Image data classification method for online training spiking neural network model along with time</title><date>2022-09-02</date><risdate>2022</risdate><abstract>The invention discloses an image data classification method for online training a pulse neural network model along with time. The method comprises the following steps: constructing a pulse neural network model and designing an online method training model along with time; the trained model is used for classifying and recognizing the image data, so that the classification and recognition performance of the image data is effectively improved; wherein the image data comprises computer image data and image visual data of the neuromorphic. Through the method provided by the invention, when the pulse neural network SNN model is trained, the overhead of a training memory can be greatly reduced, the trained model is used for visual tasks such as classification and recognition of computer image data and neuromorphic image visual data, the classification and recognition performance can be improved, the processing delay of a recognition system is reduced, and the recognition efficiency is improved. And an efficient and</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN114998659A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | Image data classification method for online training spiking neural network model along with time |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T23%3A31%3A40IST&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=HE%20DI&rft.date=2022-09-02&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114998659A%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 |