Patent · US Active

Generative neural network distillation

US11727280B2 · kind B2 · utility

1Cited by
7References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 2, 2021
Grant dateAug 15, 2023
Priority date
Expiry dateMay 27, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/82
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.

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