Chapter 9 - Learning More about GANs

1. Unlike vanilla GANs, CGAN, is a condition to both the generator and the discriminator. This condition tells the GAN what image we are expecting our generator to generate. So, both of our components—the discriminator and the generator—act upon this condition.
2. The code, c, is basically interpretable disentangled information. Assuming we have some MNIST data, then, code, c1, implies the digit label, code, c2, implies the width, c3, implies the stroke of the digit, and so on. We collectively represent them by the term c.

3. Mutual information between two random variables tells us the amount of information we can obtain from one random variable through another. Mutual information between two random variables x and y can be given as follows:

   

   It is basically the difference between the entropy of y and the conditional entropy of y...