Patent · US Active

Generative neural network distillation

US10963748B1 · kind B1 · utility

7Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 31, 2018
Grant dateMar 30, 2021
Priority date
Expiry dateFeb 18, 2039

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.