Generative Adversarial Networks (GANs) & Bayesian Networks

added 26.06.2020 13:21

by Robert R. Tucci from datasciencecentral.com

Generative Adversarial Networks (GANs) software is software for producing forgeries and imitations of data (aka synthetic data, fake data).

To gauge how widely GAN software has been used so far, see, for example, this 2019 article entitled "18 Impressive Applications of Generative Adversarial Networks (GANs)" Sounds (voices, music,...), Images (realistic pictures, paintings, drawings, handwriting, ...), Text,etc. have been faked with this software.

Here Is an example of an imaginary human face So, how is GAN software related to Bayesian Networks?

The following is a picture from that chapter, portraying a GAN Bayesian Network.

In 2017, some researchers wrote a paper entitled "Bayesian GANs" Those researchers found that their Bayesian GANs are much less sensitive than all other existing formulations.