Method and apparatus with authentication and neural network training
US11341365B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 26, 2020 |
| Grant date | May 24, 2022 |
| Priority date | — |
| Expiry date | Jul 25, 2040 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V10/776
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A processor-implemented neural network method includes: determining, using a neural network, a feature vector based on a training image of a first class among a plurality of classes; determining, using the neural network, plural feature angles between the feature vector and class vectors of other classes among the plurality of classes; determining a margin based on a class angle between a first class vector of the first class and a second class vector of a second class, among the class vectors, and a feature angle between the feature vector and the first class vector; determining a loss value using a loss function including an angle with the margin applied to the feature angle and the plural feature angles; and training the neural network by updating, based on the loss value, either one or both of one or more parameters of the neural network and one or more of the class vectors.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.