System and method for unsupervised domain adaptation via sliced-wasserstein distance
US11176477B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Dec 18, 2019 |
| Grant date | Nov 16, 2021 |
| Priority date | — |
| Expiry date | Dec 18, 2039 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N3/045
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Described is a system for unsupervised domain adaptation in an autonomous learning agent. The system adapts a learned model with a set of unlabeled data from a target domain, resulting in an adapted model. The learned model was previously trained to perform a task using a set of labeled data from a source domain. The set of labeled data has a first input data distribution, and the set of unlabeled target data has a second input data distribution that is distinct from the first input data distribution. The adapted model is implemented in the autonomous learning agent, causing the autonomous learning agent to perform the task in the target domain.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.