Systems and methods for unsupervised continual learning
US12373706B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 8, 2020 |
| Grant date | Jul 29, 2025 |
| Priority date | — |
| Expiry date | Feb 13, 2043 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Described is a system for continual adaptation of a machine learning model implemented in an autonomous platform. The system adapts knowledge previously learned by the machine learning model for performance in a new domain. The system receives a consecutive sequence of new domains comprising new task data. The new task data and past learned tasks are forced to share a data distribution in an embedding space, resulting in a shared generative data distribution. The shared generative data distribution is used to generate a set of pseudo-data points for the past learned tasks. Each new domain is learned using both the set of pseudo-data points and the new task data. The machine learning model is updated using both the set of pseudo-data points and the new task data.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.