Training a network to inhibit performance of a secondary task
US11734570B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 29, 2019 |
| Grant date | Aug 22, 2023 |
| Priority date | — |
| Expiry date | Feb 11, 2042 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06N20/00
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure describes techniques for training a neural network such that the trained network can be implemented to perform a utility task (e.g., a classification task) while inhibiting performance of a secondary task (e.g., a privacy-violating task). In some embodiments, the techniques include training a neural network using a first loss associated with a first task and a second loss associated with a second task different from the first task. In some embodiments, this includes performing a first training operation associated with the first loss, and performing a second training operation associated with the second loss, wherein the second training operation includes providing, to the neural network, a plurality of input items associated with the second task.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.