System and method for a convolutional neural network for multi-label classification with partial annotations
US12020147B2 · kind B2 · utility
0Cited by
0References
21Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Nov 15, 2019 |
| Grant date | Jun 25, 2024 |
| Priority date | — |
| Expiry date | Mar 5, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N5/01
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Effectively training machine learning systems with incomplete/partial labels is a practical, technical problem that solutions described herein attempt to overcome. In particular, an approach to modify loss functions on a proportionality basis is noted in some embodiments. In other embodiments, a graph neural network is provided to help identify correlations/causations as between categories. In another set of embodiments, a prediction approach is described to, based on originally provided labels, predict labels for unlabelled training samples such that the proportion of labelled labels relative to all labels is increased.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.