NEURAL NETWORK IMAGE CLASSIFIER

A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lampropoulos Leonidas, Criminisi Antonio, Bastani Osbert, Nori Aditya Vithal, Vytiniotis Dimitrios
Format:	Patent
Sprache:	eng
Schlagworte:	CALCULATING 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	Lampropoulos Leonidas Criminisi Antonio Bastani Osbert Nori Aditya Vithal Vytiniotis Dimitrios
description	A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine has an adversarial example generator which computes a plurality of adversarial images by, for each adversarial image, searching a region in the input space around one of the training images, the region being one in which the neural network is linear, to find an image which is incorrectly classified into the plurality of classes by the neural network. The training engine has a processor which further trains the neural network image classifier using at least the adversarial images.
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2017316281A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2017316281A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2017316281A13</originalsourceid><addsrcrecordid>eNrjZJD3cw0NcvRR8HMNCfcP8lbw9HV0d1Vw9nEMDvZ083QN4mFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgaG5saGZkYWho6GxsSpAgBc5SKR</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>NEURAL NETWORK IMAGE CLASSIFIER</title><source>esp@cenet</source><creator>Lampropoulos Leonidas ; Criminisi Antonio ; Bastani Osbert ; Nori Aditya Vithal ; Vytiniotis Dimitrios</creator><creatorcontrib>Lampropoulos Leonidas ; Criminisi Antonio ; Bastani Osbert ; Nori Aditya Vithal ; Vytiniotis Dimitrios</creatorcontrib><description>A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine has an adversarial example generator which computes a plurality of adversarial images by, for each adversarial image, searching a region in the input space around one of the training images, the region being one in which the neural network is linear, to find an image which is incorrectly classified into the plurality of classes by the neural network. The training engine has a processor which further trains the neural network image classifier using at least the adversarial images.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2017</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=20171102&DB=EPODOC&CC=US&NR=2017316281A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20171102&DB=EPODOC&CC=US&NR=2017316281A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Lampropoulos Leonidas</creatorcontrib><creatorcontrib>Criminisi Antonio</creatorcontrib><creatorcontrib>Bastani Osbert</creatorcontrib><creatorcontrib>Nori Aditya Vithal</creatorcontrib><creatorcontrib>Vytiniotis Dimitrios</creatorcontrib><title>NEURAL NETWORK IMAGE CLASSIFIER</title><description>A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine has an adversarial example generator which computes a plurality of adversarial images by, for each adversarial image, searching a region in the input space around one of the training images, the region being one in which the neural network is linear, to find an image which is incorrectly classified into the plurality of classes by the neural network. The training engine has a processor which further trains the neural network image classifier using at least the adversarial images.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2017</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZJD3cw0NcvRR8HMNCfcP8lbw9HV0d1Vw9nEMDvZ083QN4mFgTUvMKU7lhdLcDMpuriHOHrqpBfnxqcUFicmpeakl8aHBRgaG5saGZkYWho6GxsSpAgBc5SKR</recordid><startdate>20171102</startdate><enddate>20171102</enddate><creator>Lampropoulos Leonidas</creator><creator>Criminisi Antonio</creator><creator>Bastani Osbert</creator><creator>Nori Aditya Vithal</creator><creator>Vytiniotis Dimitrios</creator><scope>EVB</scope></search><sort><creationdate>20171102</creationdate><title>NEURAL NETWORK IMAGE CLASSIFIER</title><author>Lampropoulos Leonidas ; Criminisi Antonio ; Bastani Osbert ; Nori Aditya Vithal ; Vytiniotis Dimitrios</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2017316281A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2017</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Lampropoulos Leonidas</creatorcontrib><creatorcontrib>Criminisi Antonio</creatorcontrib><creatorcontrib>Bastani Osbert</creatorcontrib><creatorcontrib>Nori Aditya Vithal</creatorcontrib><creatorcontrib>Vytiniotis Dimitrios</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Lampropoulos Leonidas</au><au>Criminisi Antonio</au><au>Bastani Osbert</au><au>Nori Aditya Vithal</au><au>Vytiniotis Dimitrios</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>NEURAL NETWORK IMAGE CLASSIFIER</title><date>2017-11-02</date><risdate>2017</risdate><abstract>A training engine is described which has a memory arranged to access a neural network image classifier, the neural network image classifier having been trained using a plurality of training images from an input space, the training images being labeled for a plurality of classes. The training engine has an adversarial example generator which computes a plurality of adversarial images by, for each adversarial image, searching a region in the input space around one of the training images, the region being one in which the neural network is linear, to find an image which is incorrectly classified into the plurality of classes by the neural network. The training engine has a processor which further trains the neural network image classifier using at least the adversarial images.</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng
recordid	cdi_epo_espacenet_US2017316281A1
source	esp@cenet
subjects	CALCULATING COMPUTING COUNTING PHYSICS
title	NEURAL NETWORK IMAGE CLASSIFIER
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T16%3A56%3A22IST&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=Lampropoulos%20Leonidas&rft.date=2017-11-02&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2017316281A1%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