Title:
情報処理システム、情報処理装置、情報処理方法及び情報処理プログラム
Document Type and Number:
Japanese Patent JP7376832
Kind Code:
B2
Abstract:
A reservoir includes a common input layer, first and second output layers that outputs a first and a second readout values based on an input, a first partial reservoir including the input layer and the first output layer, and a second partial reservoir having a size between the input layer and the second output layer larger than the size of the first partial reservoir, and the training processing including: first calculating a third output weight that reduces a difference between a first product sum value of a third readout value and a first output weight; and second calculating a fourth output weight that reduces a difference between a second product sum value of a fourth readout value and a second output weight and differential teaching data that is a difference between a third product sum value of the third readout value and the third output weight and the teaching data.
Inventors:
Shoichi Miyahara
Application Number:
JP2022513781A
Publication Date:
November 09, 2023
Filing Date:
April 08, 2020
Export Citation:
Assignee:
富士通株式会社
International Classes:
G06N20/00
Domestic Patent References:
| JP2008117381A |
Foreign References:
| CN109640351A | ||||
| CN109009033A |
Other References:
秋山貴則, 外1名,“多段階学習Echo state networkによる非線形時系列予測”,電子情報通信学会技術研究報告,日本,一般社団法人電子情報通信学会,2018年10月29日,第118巻, 第284号,p.293-299
Meftah, Boudjelal, Olivier Lezoray, and Abdelkader Benyettou.,Novel approach using echo state networks for microscopic cellular image segmentation.,Cognitive Computation [Online],Volume 8, Issue 2,2015年08月30日,p.237-245,インターネット:,[検索日 2020.07.15]
Meftah, Boudjelal, Olivier Lezoray, and Abdelkader Benyettou.,Novel approach using echo state networks for microscopic cellular image segmentation.,Cognitive Computation [Online],Volume 8, Issue 2,2015年08月30日,p.237-245,インターネット:
Attorney, Agent or Firm:
Patent Attorney Corporation Fields International Patent Office