Re:Ideas in statistics that have powered AI
by nancarrow on Wednesday July 07, 2021 @10:36PM
(#27767965)
The generator implicitly models a joint probability of data by being a generative process that one can draw samples from. GAN training (at least under certain simplifying assumptions) minimizes the JS divergence between the generator distribution and the data distribution.
[ Parent
| on HN ]
There are no comments on this comment yet.