The loss function of the generator is given as follows:

We know that the goal of the generator is to fool the discriminator to classify the fake image as a real image.

In the Discriminator loss section, we saw that implies the probability of classifying the fake input image as a fake image, and the discriminator maximizes the probabilities for correctly classifying the fake image as fake.

But the generator wants to minimize this probability. As the generator wants to fool the discriminator, it minimizes this probability of a fake input image being classified as fake by the discriminator. Thus, the loss function of the generator can be expressed as follows: