Generative Adversarial Networks in Detail

Understand the core principles behind Generative Adversarial Networks by exploring how the generator creates fake data to mimic real data distributions while fooling the discriminator. Learn about the adversarial loss function and the minimax game training process that drives unsupervised learning in GANs.

We'll cover the following...

Training
The math

Another way to explain GANs is through the probabilistic formulation we used on variational autoencoders.

GANs follow a different approach in finding the probability distribution of the data $p_{data}(x)$ .

Instead of computing or the approximate $p_{data}(x)$ , we only care about the ability to sample data from the distribution.

But what does that actually mean?

If we assume that our data $x_i$ follow a probability distribution $p_{data}(x)$ , we will want to build a model that allows us to draw samples from $p_{data}(x)$ .

As we did with VAE, we again introduce a latent variable $z$ with a prior distribution $p(z)$ . $p(z)$ is usually a simple ...

1.Learn Deep Learning

2.Neural Networks

3.Training Neural Networks

4.Convolutional Neural Networks

5.Recurrent Neural Networks

6.Autoencoders

7.Generative Adversarial Networks

8.Attention and Transformers

9.Graph Neural Networks

10.Conclusion

Assessment

Generative Adversarial Networks in Detail