Method for training and testing data embedding network to generate marked data by integrating original data with mark data, and training device and testing device using the same
US10789551B2 · kind B2 · utility
Assignee
Inventor
Key dates
| Filing date | Jul 17, 2019 |
| Grant date | Sep 29, 2020 |
| Priority date | — |
| Expiry date | Jul 17, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG10L19/018
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method for learning a data embedding network is provided. The method includes steps of: a learning device acquiring and inputting original training data and mark training data into the data embedding network which integrates them and generates marked training data; inputting the marked training data into a learning network which applies a network operation to them and generates 1-st characteristic information, and inputting the original training data into the learning network which applies a network operation to them and generates 2-nd characteristic information; learning the data embedding network such that a data error is minimized, by referring to part of errors referring to the 1-st and the 2-nd characteristic information and errors referring to task specific outputs and their ground truths, and a marked data score is maximized, and learning a discriminator such that a original data score is maximized and the marked data score is minimized.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.