Patent · US Active

Training a network to inhibit performance of a secondary task

US11734570B1 · kind B1 · utility

4Cited by
0References
24Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 29, 2019
Grant dateAug 22, 2023
Priority date
Expiry dateFeb 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.