LEARNING DEVICE, DETERMINATION DEVICE, LEARNING METHOD, AND RECORDING MEDIUM

Title:

LEARNING DEVICE, DETERMINATION DEVICE, LEARNING METHOD, AND RECORDING MEDIUM

Document Type and Number:

WIPO Patent Application WO/2023/233559

Kind Code:

A1

Abstract:

This learning device is provided with: a mask initializing means for determining, among parameters in a machine learning model having a plurality of parameters, mask information indicating the difference between shared parameters provided for common use among a plurality of the machine learning models and non-shared parameters provided to each machine learning model individually; a loss function calculation means for calculating the value of a loss function based on the plurality of machine learning models by using training data; and a parameter updating means for using the value of the loss function to update the values of the shared parameters and the values of the non-shared parameters.

More Like This:

WO/2023/113401	TRAINING METHOD USING USER-CENTERED ARTIFICIAL INTELLIGENCE
WO/2020/213425	STATE ESTIMATION DEVICE, STATE ESTIMATION PROGRAM, ESTIMATION MODEL, AND STATE ESTIMATION METHOD
WO/2023/146659	GENERATING A CONFIGURATION PORTFOLIO INCLUDING A SET OF MODEL CONFIGURATIONS

Inventors:

KAKIZAKI KAZUYA (JP)
FURUKAWA JUN (JP)
ARAKI TOSHINORI (JP)

Application Number:

PCT/JP2022/022235

Publication Date:

December 07, 2023

Filing Date:

May 31, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

NEC CORP (JP)

International Classes:

G06N20/20

Foreign References:

JP2021101318A	2021-07-08
US20170024642A1	2017-01-26

Other References:

AMADA TAKUMA, KAKIZAKI KAZUYA, ARAKI TOSHINORI, LIEW SENG PEI, KESHET JOSEPH, FURUKAWA JUN: "Adversarial Robustness for Face Recognition: How to Introduce Ensemble Diversity among Feature Extractors?", 1 January 2021 (2021-01-01), XP093116055, Retrieved from the Internet
MADA, TAKUMA; KAKIZAKI, KAZUYA; LIEW, SENG PEI; FURUKAWA, JUN; ARAKI, TOSHINORI; KESHET, JOSPEH: "Improving Adversarial Robustness on Face Recognition Systems", COMPUTER SECURITY SYMPOSIUM 2020; OCTOBER 26-29, 2020, INFORMATION PROCESSING SOCIETY OF JAPAN (IPSJ), 19 October 2020 (2020-10-19) - 29 October 2020 (2020-10-29), pages 129 - 136, XP009551514

Attorney, Agent or Firm:

TANAI Sumio et al. (JP)

Download PDF:

View/Download PDF PDF Help

Previous Patent: METHOD FOR PRODUCING PREPOLYMER SOLUTION AND METHOD FOR PRODUCING INSULATED WIRE

Next Patent: ATTACK ANALYSIS DEVICE, ATTACK ANALYSIS METHOD, AND ATTACK ANALYSIS PROGRAM