Patent · US Active

Autoencoding generative adversarial network for augmenting training data usable to train predictive models

US12254414B2 · kind B2 · utility

0Cited by

2References

16Claims

0Family size

Assignee

Tobii AB · SE

Inventor

Mårten Nilsson · Danderyd, SE

Key dates

Filing date	May 13, 2019
Grant date	Mar 18, 2025
Priority date	—
Expiry date	Jun 13, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/094
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Techniques for using a deep generative model to generate synthetic data sets that can be used to boost the performance of a discriminative model are described. In an example, an autoencoding generative adversarial network (AEGAN) is trained to generate the synthetic data sets. The AEGAN includes an autoencoding network and a generative adversarial network (GAN) that share a generator. The generator learns how to the generate synthetic data sets based on a data distribution from a latent space. Upon training the AEGAN, the generator generates the synthetic data sets. In turn, the synthetic data sets are used to train a predictive model, such as a convolutional neural network for gaze prediction.

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