Using a GAN to Generate Photos of Cats

A lot of the time with machine learning algorithms, it's really hard to predict ahead of time how well they'll actually perform. I would say I still today don't have one factor I can put my finger on why GANs worked for photo generation and deep bolts and machines don't. There are a lot of theory papers showing that under some theoretical settings, the GAN algorithm does actually converge. But those settings are restricted enough that they don't necessarily explain the whole picture in terms of all the results that we see in practice.