Machine learning using informed pseudolabels
US11669724B2 · kind B2 · utility
1Cited by
15References
10Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | May 16, 2019 |
| Grant date | Jun 6, 2023 |
| Priority date | — |
| Expiry date | Feb 5, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/044
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Subject matter regards improving machine learning techniques using informed pseudolabels. A method can include receiving previously assigned labels indicating an expected classification for data, the labels having a specified uncertainty, generating respective pseudolabels for the data based on the previously assigned labels, the data, a class vector determined by an ML model, and a noise model indicating, based on the specified uncertainty, a likelihood of the previously assigned label given the class, and substituting the pseudolabels for the previously assigned labels in a next epoch of training the ML model.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.