MACHINE LEARNING DEVICE, MACHINE LEARNING SYSTEM, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM

Provided with a technology of a machine learning using a convolutional neural network depending on practical calculation cost and security level desired by a user. A machine learning device includes: a data acquisition unit configured to acquire an image data; and a machine learning calculation unit...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: MIHARA, Kentaro
Format: Patent
Sprache:eng ; fre ; ger
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 MIHARA, Kentaro
description Provided with a technology of a machine learning using a convolutional neural network depending on practical calculation cost and security level desired by a user. A machine learning device includes: a data acquisition unit configured to acquire an image data; and a machine learning calculation unit configured to execute a calculation based on the image data using a convolutional neural network, wherein the convolutional neural network comprises a plurality of layers, the machine learning calculation unit includes: an encryption processing unit configured to execute the calculation by a homomorphic encryption in an encryption execution area; a plaintext processing unit configured to execute the calculation in a plaintext encryption area; and a reception unit configured to receive a layer designation information for designating an N-th layer which is an intermediate layer between an input layer and an output layer of the convolutional neural network, the encryption processing unit is configured to execute the calculation from the input layer to the N-th layer, and the plaintext processing unit is configured to execute the calculation from the (N+1)-th layer to the output layer.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP4296897A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP4296897A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP4296897A13</originalsourceid><addsrcrecordid>eNrjZEj3dXT28PRzVfBxdQzy8_RzV3BxDfN0dtVRwJAIjgwOcfXFIuHrGuLh76Kj4OjngikZEOTvHuToy8PAmpaYU5zKC6W5GRTcXEOcPXRTC_LjU4sLEpNT81JL4l0DTIwszSwszR0NjYlQAgAnCzRp</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MACHINE LEARNING DEVICE, MACHINE LEARNING SYSTEM, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM</title><source>esp@cenet</source><creator>MIHARA, Kentaro</creator><creatorcontrib>MIHARA, Kentaro</creatorcontrib><description>Provided with a technology of a machine learning using a convolutional neural network depending on practical calculation cost and security level desired by a user. A machine learning device includes: a data acquisition unit configured to acquire an image data; and a machine learning calculation unit configured to execute a calculation based on the image data using a convolutional neural network, wherein the convolutional neural network comprises a plurality of layers, the machine learning calculation unit includes: an encryption processing unit configured to execute the calculation by a homomorphic encryption in an encryption execution area; a plaintext processing unit configured to execute the calculation in a plaintext encryption area; and a reception unit configured to receive a layer designation information for designating an N-th layer which is an intermediate layer between an input layer and an output layer of the convolutional neural network, the encryption processing unit is configured to execute the calculation from the input layer to the N-th layer, and the plaintext processing unit is configured to execute the calculation from the (N+1)-th layer to the output layer.</description><language>eng ; fre ; ger</language><subject>ADVERTISING ; CALCULATING ; CODING OR CIPHERING APPARATUS FOR CRYPTOGRAPHIC OR OTHERPURPOSES INVOLVING THE NEED FOR SECRECY ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; CRYPTOGRAPHY ; DISPLAY ; EDUCATION ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS ; SEALS</subject><creationdate>2023</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&amp;date=20231227&amp;DB=EPODOC&amp;CC=EP&amp;NR=4296897A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20231227&amp;DB=EPODOC&amp;CC=EP&amp;NR=4296897A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>MIHARA, Kentaro</creatorcontrib><title>MACHINE LEARNING DEVICE, MACHINE LEARNING SYSTEM, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM</title><description>Provided with a technology of a machine learning using a convolutional neural network depending on practical calculation cost and security level desired by a user. A machine learning device includes: a data acquisition unit configured to acquire an image data; and a machine learning calculation unit configured to execute a calculation based on the image data using a convolutional neural network, wherein the convolutional neural network comprises a plurality of layers, the machine learning calculation unit includes: an encryption processing unit configured to execute the calculation by a homomorphic encryption in an encryption execution area; a plaintext processing unit configured to execute the calculation in a plaintext encryption area; and a reception unit configured to receive a layer designation information for designating an N-th layer which is an intermediate layer between an input layer and an output layer of the convolutional neural network, the encryption processing unit is configured to execute the calculation from the input layer to the N-th layer, and the plaintext processing unit is configured to execute the calculation from the (N+1)-th layer to the output layer.</description><subject>ADVERTISING</subject><subject>CALCULATING</subject><subject>CODING OR CIPHERING APPARATUS FOR CRYPTOGRAPHIC OR OTHERPURPOSES INVOLVING THE NEED FOR SECRECY</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>CRYPTOGRAPHY</subject><subject>DISPLAY</subject><subject>EDUCATION</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><subject>SEALS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZEj3dXT28PRzVfBxdQzy8_RzV3BxDfN0dtVRwJAIjgwOcfXFIuHrGuLh76Kj4OjngikZEOTvHuToy8PAmpaYU5zKC6W5GRTcXEOcPXRTC_LjU4sLEpNT81JL4l0DTIwszSwszR0NjYlQAgAnCzRp</recordid><startdate>20231227</startdate><enddate>20231227</enddate><creator>MIHARA, Kentaro</creator><scope>EVB</scope></search><sort><creationdate>20231227</creationdate><title>MACHINE LEARNING DEVICE, MACHINE LEARNING SYSTEM, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM</title><author>MIHARA, Kentaro</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP4296897A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2023</creationdate><topic>ADVERTISING</topic><topic>CALCULATING</topic><topic>CODING OR CIPHERING APPARATUS FOR CRYPTOGRAPHIC OR OTHERPURPOSES INVOLVING THE NEED FOR SECRECY</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>CRYPTOGRAPHY</topic><topic>DISPLAY</topic><topic>EDUCATION</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><topic>SEALS</topic><toplevel>online_resources</toplevel><creatorcontrib>MIHARA, Kentaro</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>MIHARA, Kentaro</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MACHINE LEARNING DEVICE, MACHINE LEARNING SYSTEM, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM</title><date>2023-12-27</date><risdate>2023</risdate><abstract>Provided with a technology of a machine learning using a convolutional neural network depending on practical calculation cost and security level desired by a user. A machine learning device includes: a data acquisition unit configured to acquire an image data; and a machine learning calculation unit configured to execute a calculation based on the image data using a convolutional neural network, wherein the convolutional neural network comprises a plurality of layers, the machine learning calculation unit includes: an encryption processing unit configured to execute the calculation by a homomorphic encryption in an encryption execution area; a plaintext processing unit configured to execute the calculation in a plaintext encryption area; and a reception unit configured to receive a layer designation information for designating an N-th layer which is an intermediate layer between an input layer and an output layer of the convolutional neural network, the encryption processing unit is configured to execute the calculation from the input layer to the N-th layer, and the plaintext processing unit is configured to execute the calculation from the (N+1)-th layer to the output layer.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; fre ; ger
recordid cdi_epo_espacenet_EP4296897A1
source esp@cenet
subjects ADVERTISING
CALCULATING
CODING OR CIPHERING APPARATUS FOR CRYPTOGRAPHIC OR OTHERPURPOSES INVOLVING THE NEED FOR SECRECY
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
CRYPTOGRAPHY
DISPLAY
EDUCATION
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
SEALS
title MACHINE LEARNING DEVICE, MACHINE LEARNING SYSTEM, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T04%3A21%3A48IST&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=MIHARA,%20Kentaro&rft.date=2023-12-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP4296897A1%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