Multiple task transfer learning
US11829869B2 · kind B2 · utility
1Cited by
1References
16Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Jul 25, 2019 |
| Grant date | Nov 28, 2023 |
| Priority date | — |
| Expiry date | Sep 22, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/2528
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Systems and methods relating to multitask transfer learning. Neural networks are used to accomplish a number of tasks and the results of these tasks are used to determine parameters common to these and other tasks. These parameters can then be used to accomplish other related tasks. In the description, data fitting as well as image related tasks are used. Task conditioning as well as the use of a KL regularizer have greatly improved results when testing the methods of the invention.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.