New preprint: Throw out bad GAN samples when sampling (using the discriminator to tell good from bad). Quality goes up. An easy win!https://twitter.com/gstsdn/status/1052366996887592962 …
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
re 'imitating human visual system' - are you perhaps thinking of doing pairwise comparisons a la 'learning from preferences'? The D is already effectively doing pairwise comparisons with generated vs real samples, so you could plug in human pairwise comparisons on generateds.
Something like that is definitely a possibility!
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.