#objective

Question 1: Single choice

mediumAI-checkedGenerative Adversarial Networks

A conditional GAN must generate digits of a requested class $y$ (e.g. MNIST label 7), and its discriminator judges whether an image is a real example of that class. Which objective describes it?

$\min_G \max_D\; \mathbb{E}_{x}[\log D(x \mid y)] + \mathbb{E}_{z}[\log(1 - D(G(z \mid y)))]$ 1
$\min_G \max_D\; \mathbb{E}_{x}[\log D(x)] + \mathbb{E}_{z}[\log(1 - D(G(z \mid y)))]$ 2
$\min_G \max_D\; \mathbb{E}_{x}[\log D(x \mid y)] + \mathbb{E}_{z}[\log(1 - D(G(z)))]$ 3
$\min_D \max_G\; \mathbb{E}_{x}[\log D(x \mid y)] + \mathbb{E}_{z}[\log(1 - D(G(z \mid y)))]$ 4

Timed test