In this article, the author talks about how deeplearning models no longer are trained for an objective function that humans specify, but find their own objective function. Specifically, he is talking about GANs.

Is there a good resource explaining this idea that GANs find their own objective function? Based on what I've read about GANs, I don't think of them this way.

  • $\begingroup$ Judging by the fact that this article references specific research papers, I would imagine those would be the best resource for explanation of their methods. $\endgroup$
    – Ethan
    Feb 15 '19 at 21:23
  • $\begingroup$ @Ethan, they did not seem to go deeper into the specific point that "the objective function is emerged at dynamically". Rather they conceptualize it in terms of nash equilibria. $\endgroup$
    – user637140
    Feb 16 '19 at 9:43

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.