TOP > 外国特許検索 > NEURAL NETWORK PROCESSING DEVICE, COMPUTER PROGRAM, NEURAL NETWORK MANUFACTURING METHOD, NEURAL NETWORK DATA MANUFACTURING METHOD, NEURAL NETWORK USE DEVICE, AND NEURAL NETWORK DOWNSCALING METHOD

NEURAL NETWORK PROCESSING DEVICE, COMPUTER PROGRAM, NEURAL NETWORK MANUFACTURING METHOD, NEURAL NETWORK DATA MANUFACTURING METHOD, NEURAL NETWORK USE DEVICE, AND NEURAL NETWORK DOWNSCALING METHOD

Foreign code F200010230
File No. (S2018-0979-N0)
Posted date 2020年10月29日
Country 世界知的所有権機関(WIPO)
International application number 2019JP033594
International publication number WO2020054402
Date of international filing 令和元年8月28日(2019.8.28)
Date of international publication 令和2年3月19日(2020.3.19)
Priority data
  • 特願2018-169412 (2018.9.11) JP
  • 特願2019-059091 (2019.3.26) JP
Title NEURAL NETWORK PROCESSING DEVICE, COMPUTER PROGRAM, NEURAL NETWORK MANUFACTURING METHOD, NEURAL NETWORK DATA MANUFACTURING METHOD, NEURAL NETWORK USE DEVICE, AND NEURAL NETWORK DOWNSCALING METHOD
Abstract An objective of the present invention is to alleviate a degradation in neural network performance at the time of downscaling. A neural network processing device 10 according to the present disclosure is configured to execute: a process 22 of providing a plurality of instances of input data 40 to a neural network N1 in which a plurality of artificial neurons are connected and deriving vectors formed from a plurality of outputs outputted from the artificial neurons for each of the artificial neurons; and an integration process 23 of, on the basis of the vectors, selecting a plurality of artificial neurons which demonstrate identical or similar behavior, and integrating the selected artificial neurons.
Outline of related art and contending technology BACKGROUND ART
Such as deep neural networks the neural network, a plurality of artificial neurons (hereinafter, referred to as' neuron ') is combined with a computing mechanism. Provide a large amount of data to the neural network, neurons each of which is connected to the optimization calculations of the weight coefficient of the deep layer can be referred to as learning.
  • Applicant
  • ※All designated countries except for US in the data before July 2012
  • WAKAYAMA UNIVERSITY
  • Inventor
  • WADA Toshikazu
  • KAMMA Koji
  • ISODA Yuuki
IPC(International Patent Classification)
Specified countries National States: AE AG AL AM AO AT AU AZ BA BB BG BH BN BR BW BY BZ CA CH CL CN CO CR CU CZ DE DJ DK DM DO DZ EC EE EG ES FI GB GD GE GH GM GT HN HR HU ID IL IN IR IS JO JP KE KG KH KN KP KR KW KZ LA LC LK LR LS LU LY MA MD ME MG MK MN MW MX MY MZ NA NG NI NO NZ OM PA PE PG PH PL PT QA RO RS RU RW SA SC SD SE SG SK SL SM ST SV SY TH TJ TM TN TR TT TZ UA UG US UZ VC VN ZA ZM ZW
ARIPO: BW GH GM KE LR LS MW MZ NA RW SD SL SZ TZ UG ZM ZW
EAPO: AM AZ BY KG KZ RU TJ TM
EPO: AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR
OAPI: BF BJ CF CG CI CM GA GN GQ GW KM ML MR NE SN ST TD TG

PAGE TOP

close
close
close
close
close
close