OPERATION METHOD FOR ARTIFICIAL NEURAL NETWORK

An operation method of an artificial neural network is provided. The operation method includes: dividing input information into a plurality of sub-input information, and expanding kernel information to generate expanded kernel information; performing a Fast Fourier Transform (FFT) on the sub-input i...

Full description

Saved in:
Bibliographic Details
Main Authors Wang, Wei-Chen, Ho, Chien-Chung, Ho, Shu-Yin, Chang, Yuan-Hao
Format Patent
LanguageEnglish
Published 27.05.2021
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

Abstract An operation method of an artificial neural network is provided. The operation method includes: dividing input information into a plurality of sub-input information, and expanding kernel information to generate expanded kernel information; performing a Fast Fourier Transform (FFT) on the sub-input information and the expanded kernel information to respectively generate a plurality of frequency domain sub-input information and frequency domain expanded kernel information; respectively performing a multiplying operation on the frequency domain expanded kernel information and the frequency domain sub-input information to respectively generate a plurality of sub-feature maps; and performing an inverse FFT on the sub-feature maps to provide a plurality of converted sub-feature maps for executing a feature extraction operation of the artificial neural network.
AbstractList An operation method of an artificial neural network is provided. The operation method includes: dividing input information into a plurality of sub-input information, and expanding kernel information to generate expanded kernel information; performing a Fast Fourier Transform (FFT) on the sub-input information and the expanded kernel information to respectively generate a plurality of frequency domain sub-input information and frequency domain expanded kernel information; respectively performing a multiplying operation on the frequency domain expanded kernel information and the frequency domain sub-input information to respectively generate a plurality of sub-feature maps; and performing an inverse FFT on the sub-feature maps to provide a plurality of converted sub-feature maps for executing a feature extraction operation of the artificial neural network.
Author Ho, Shu-Yin
Ho, Chien-Chung
Chang, Yuan-Hao
Wang, Wei-Chen
Author_xml – fullname: Wang, Wei-Chen
– fullname: Ho, Chien-Chung
– fullname: Ho, Shu-Yin
– fullname: Chang, Yuan-Hao
BookMark eNrjYmDJy89L5WTQ8w9wDXIM8fT3U_B1DfHwd1Fw8w9ScAwK8XTzdPZ09FHwcw0NAlMh4f5B3jwMrGmJOcWpvFCam0HZzTXE2UM3tSA_PrW4IDE5NS-1JD402MjAyNDQ1MLQzMDR0Jg4VQCAwCh9
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US2021158160A1
GroupedDBID EVB
ID FETCH-epo_espacenet_US2021158160A13
IEDL.DBID EVB
IngestDate Fri Oct 11 05:31:48 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US2021158160A13
Notes Application Number: US202017096575
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210527&DB=EPODOC&CC=US&NR=2021158160A1
ParticipantIDs epo_espacenet_US2021158160A1
PublicationCentury 2000
PublicationDate 20210527
PublicationDateYYYYMMDD 2021-05-27
PublicationDate_xml – month: 05
  year: 2021
  text: 20210527
  day: 27
PublicationDecade 2020
PublicationYear 2021
RelatedCompanies MACRONIX International Co., Ltd
RelatedCompanies_xml – name: MACRONIX International Co., Ltd
Score 3.3286293
Snippet An operation method of an artificial neural network is provided. The operation method includes: dividing input information into a plurality of sub-input...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Title OPERATION METHOD FOR ARTIFICIAL NEURAL NETWORK
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20210527&DB=EPODOC&locale=&CC=US&NR=2021158160A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED_G_HzTqvgxpaD0rbp-pOkehmz9YFO7jq3VvY22SUGQbtiK_77XuOme9hSSQLiE3MfvLncBuGtzZhJiczVJLEPFG5KriW5SlTLe6bBUY3ZWJzgHI2sQm08zMmvAxzoXRtQJ_RbFEZGjMuT3Ssjr5b8TyxVvK8uH9B2HFo9-1HWVFTpG_EJ0qrj9rjcO3dBRHKcbT5XRRMxpxNasdg-x0g4a0lTAttd-nZey3FQq_hHsjnG9ojqGBi8kOHDWf69JsB-sQt4S7Ik3mlmJgys-LE_gPhx7v94lOfCiQejKCOZktE2H_tAZ9l7kkRdPRBO9hZPnU7j1vcgZqEjC_G_H83i6Sa9xBs1iUfBzkJOE0ZzYearTzGS6mRoWSghOMq5lhKX0AlrbVrrcPn0Fh3W3Do7rtAXN6vOLX6POrdIbcVQ_0meAaw
link.rule.ids 230,309,783,888,25577,76883
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEL8Q_MA3RY0fqEs0e5uysW7jgRjYRzZhG4FNeVu2tSQmZhCZ8d_3VkF54qnJXXJpm95df9e7K8BDm1GVEINJaap1JDwhcylVVF3SKet2aSZTI68KnP1Ac2P1ZUZmNfjY1MLwPqHfvDkialSO-l5ye738D2JZPLdy9ZS9I2nx7EQ9S1yjY8QvRNFFa9Czx6EVmqJp9uKpGEw4TyaGrLX7iJX28JJtcLD0OqjqUpbbTsU5hv0xyivKE6ixogkNc_P3WhMO_fWTdxMOeI5mvkLiWg9Xp_AYju3f6JLg25EbWgKCOQHvpp7jmV5_JAR2POFD9BZOhmdw79iR6Uo4heRvxUk83Z5v5xzqxaJgFyCkKdXnxJhnip6rVFGzjoYWgpGcyTmhmX4JrV2Srnaz76DhRv4oGXnB8BqOKlb1UK7oLaiXn1_sBv1vmd3ybfsBAAiDWw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=OPERATION+METHOD+FOR+ARTIFICIAL+NEURAL+NETWORK&rft.inventor=Wang%2C+Wei-Chen&rft.inventor=Ho%2C+Chien-Chung&rft.inventor=Ho%2C+Shu-Yin&rft.inventor=Chang%2C+Yuan-Hao&rft.date=2021-05-27&rft.externalDBID=A1&rft.externalDocID=US2021158160A1