Patent · US Active

Generating more realistic synthetic data with adversarial nets

US11475276B1 · kind B1 · utility

9Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 6, 2017
Grant dateOct 18, 2022
Priority date
Expiry dateJun 13, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F18/28
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A generative network may be learned in an adversarial setting with a goal of modifying synthetic data such that a discriminative network may not be able to reliably tell the difference between refined synthetic data and real data. The generative network and discriminative network may work together to learn how to produce more realistic synthetic data with reduced computational cost. The generative network may iteratively learn a function that synthetic data with a goal of generating refined synthetic data that is more difficult for the discriminative network to differentiate from real data, while the discriminative network may be configured to iteratively learn a function that classifies data as either synthetic or real. Over multiple iterations, the generative network may learn to refine the synthetic data to produce refined synthetic data on which other machine learning models may be trained.

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