公开(公告)号：US11281993B2

公开(公告)日：2022-03-22

申请号：US15832671

申请日：2017-12-05

Applicant: Apple Inc.

Inventor： Joshua M. Susskind ,  Feng Tang ,  Chen Huang ,  Shih-Yu Sun ,  Walter A. Talbot

IPC: G06F3/0488 ,  G06N20/00 ,  G06F3/04883 ,  G06N5/02 ,  G06F3/04817

Abstract: Systems and processes for metric learning distillation are disclosed herein. In accordance with one example, a method includes, at an electronic device, at an electronic device having one or more processors and memory, receiving a first plurality of vectors from a first model, receiving a second plurality of vectors from a second model, determining a first plurality of vector distances based on the first plurality of vectors, generating a first matrix based on the first plurality of vector distances, determining a second plurality of vector distances based on the second plurality of vectors, generating a second matrix based on the second plurality of vector distances, comparing the first matrix with the second matrix, and adjusting the second model based on the comparison of the first matrix and the second matrix.

公开(公告)号：US20180157992A1

公开(公告)日：2018-06-07

申请号：US15832671

申请日：2017-12-05

Applicant: Apple Inc.

Inventor： Joshua M. Susskind ,  Feng Tang ,  Chen Huang ,  Shih-Yu Sun ,  Walter A. Talbot

IPC: G06N99/00 ,  G06N5/02

CPC classification number: G06N20/00 ,  G06F3/04817 ,  G06F3/04883 ,  G06N5/02

Abstract: Systems and processes for metric learning distillation are disclosed herein. In accordance with one example, a method includes, at an electronic device, at an electronic device having one or more processors and memory, receiving a first plurality of vectors from a first model, receiving a second plurality of vectors from a second model, determining a first plurality of vector distances based on the first plurality of vectors, generating a first matrix based on the first plurality of vector distances, determining a second plurality of vector distances based on the second plurality of vectors, generating a second matrix based on the second plurality of vector distances, comparing the first matrix with the second matrix, and adjusting the second model based on the comparison of the first matrix and the second matrix.