Patent · US Active

System and method for knowledge distillation between neural networks

US11636337B2 · kind B2 · utility

0Cited by
2References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 20, 2020
Grant dateApr 25, 2023
Priority date
Expiry dateMay 17, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/096
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods for knowledge distillation provide supervised training of a student network with a teacher network, including inputting a batch to the teacher network, inputting the batch to the student network, generating a teacher activation map at a layer of the teacher network, generating a student activation map at a layer of the student network corresponding to the layer of the teacher network, generating a pairwise teacher similarity matrix based on the teacher activation map, generating a pairwise student similarity matrix based on the student activation map, and minimizing a knowledge distillation loss defined as a difference between the pairwise teacher similarity matrix and the pairwise student similarity matrix.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.