公开(公告)号：US11734570B1

公开(公告)日：2023-08-22

申请号：US16666850

申请日：2019-10-29

Applicant: Apple Inc.

Inventor： Daniel Kurz ,  Thomas Gebauer ,  Dewey H. Lee ,  Muhammad Ahmed Riaz ,  Qian Wang

IPC: G06N3/084 ,  G06F9/48 ,  G06N20/00 ,  G06N5/046

CPC classification number: G06N3/084 ,  G06F9/48 ,  G06N5/046 ,  G06N20/00

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.