MACHINE LEARNING DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM

Title:

MACHINE LEARNING DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM

Document Type and Number:

WIPO Patent Application WO/2023/053569

Kind Code:

A1

Abstract:

Provided is a machine learning device (200) that continuously learns a small number of new classes compared to the base classes. A base class feature extraction unit (50) extracts a feature vector of the base classes. A new class feature extraction unit (52) extract a feature vector of the new classes. A mixed feature calculation unit (60) mixes the feature vector of the base classes with the feature vector of the new classes to calculate a mixed feature vector of the base classes and the new classes. A learning unit (80) classifies a query sample in a query set on the basis of the distance between the position of the mixed feature vector of the query sample of the query set and the position of a classification weight vector for each class in a projection space, and learns a classification weight vector of the new classes so as to minimize classification loss.

More Like This:

JP2022184272	INFORMATION PROCESSOR, INFORMATION PROCESSING METHOD AND PROGRAM
JP2022111038	OPTICAL INFORMATION READER
JP7032376	Learning entity trust model and / or risk tolerance for risk score calculation

Inventors:

KIDA SHINGO (JP)
TAKEHARA HIDEKI (JP)
YANG YINCHENG (JP)
TAKAMI MAKI (JP)

Application Number:

PCT/JP2022/021173

Publication Date:

April 06, 2023

Filing Date:

May 24, 2022

Export Citation:

Click for automatic bibliography generation Help

Assignee:

JVCKENWOOD CORP (JP)

International Classes:

G06N20/00

Foreign References:

CN113159116A	2021-07-23
CN113095446A	2021-07-09

Other References:

SUNG WHAN YOON; DO-YEON KIM; JUN SEO; JAEKYUN MOON: "XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning", ARXIV.ORG, 1 July 2020 (2020-07-01), XP081714696