Excellent explanation.
katy sei

Thanks. I think that is the interesting part of of GAN. The discriminator and generator must learn together. It is not conflicting but mutually beneficial. If the discriminator learns faster than the generator, the generator learning process suffers since it needs the discriminator backprop feedback to improve its parameters.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.