Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
IDENTIFICATION DEVICE, IDENTIFICATION METHOD, AND RECORDING MEDIUM
Document Type and Number:
WIPO Patent Application WO/2021/220450
Kind Code:
A1
Abstract:
An identification device (2) comprises: an identification means (21) for identifying the class of input data using a learnable learning model (M); and an updating means (22) for updating the learning model using an objective function (L) that is based on a first index value for evaluating the accuracy of the results of identifying the class of the input data, and a second index value for evaluating the amount of time required to identify the class of the input data.

Inventors:
MIYAGAWA TAIKI (JP)
EBIHARA AKINORI (JP)
Application Number:
PCT/JP2020/018236
Publication Date:
November 04, 2021
Filing Date:
April 30, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
NEC CORP (JP)
International Classes:
G06N20/00
Domestic Patent References:
WO2019049688A12019-03-14
Foreign References:
JP2019164618A2019-09-26
Other References:
WENLIN WANG; CHANGYOU CHEN; WENQI WANG; PIYUSH RAI; LAWRENCE CARIN: "Earliness-Aware Deep Convolutional Networks for Early Time Series Classification", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 14 November 2016 (2016-11-14), 201 Olin Library Cornell University Ithaca, NY 14853 , XP080731719
MARC RU{\SS}WURM; S\EBASTIEN LEF\`EVRE; NICOLAS COURTY; R\EMI EMONET; MARCO K\"ORNER; ROMAIN TAVENARD: "End-to-end Learning for Early Classification of Time Series", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 30 January 2019 (2019-01-30), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081009992
Attorney, Agent or Firm:
EGAMI, TATSUO et al. (JP)
Download PDF: