Patent · US Active

Learning method and processing apparatus regarding machine learning model classifying input image

US12236667B2 · kind B2 · utility

0Cited by
3References
8Claims
0Family size

Assignees

Inventors

Key dates

Filing dateAug 24, 2022
Grant dateFeb 25, 2025
Priority date
Expiry dateJul 25, 2043

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/084
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method by one or more computers for learning a machine learning model classifying an input image into known classes and an unknown class by extracting a feature of the input image. The method comprises acquiring a set of features of a plurality of samples of training data each of which is with a label, calculating a loss function based on the set of the features, and learning the machine learning model to reduce the loss function. The loss function is calculated to include a first loss function and a second loss function. The first loss function is configured to become larger as first distances become smaller than a predetermined margin. The second loss function is configured to become larger as second distances become larger and as third distances become smaller.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.