Contents

## Which one should you choose GAN or VAE?

By rigorous definition, VAE models explicitly learn likelihood distribution P(X|Y) through loss function. GAN does not explicitly learn likelihood distribution. But GAN generators serve to generate images that could fool the discriminator. In this sense, GAN explicitly learns the likelihood distributions.

## Is GAN Encoder Decoder?

The encoder encodes the data and the decoder tries to reconstruct the data back using the internal representations and the learned weights. Whereas GANs work on a generative principle and try to learn from data distributions to use a game theory approach to build great models.

## What’s the difference between a Gan and a VAE Gan?

To reiterate what I said previously about the VAE-GAN, the term VAE-GAN was first used by Larsen et. al in their paper “Autoencoding beyond pixels using a learned similarity metric”. VAE-GAN models differentiate themselves from GANs in that their generators are variation autoencoders.

## How are Vaes and Gans used in machine learning?

Just like VAEs, GANs belong to a class of generative algorithms that are used in unsupervised machine learning. Typical GANs consist of two neural networks, a generative neural network and a discriminative neural network. A generative neural network is responsible for taking noise as input and generating samples.

## What’s the goal of a VAE-Gan data generator?

The major goal of generators is to generate data that increasingly “fools” the discriminative neural network, i.e. increasing its error rate. This can be done by repeatedly generating samples that appear to be from the training data distribution. A simple way to visualize this is the “competition” between a cop and a cyber criminal.

## Can a Gan discriminator be used as a VAE decoder?

The authors suggested a GAN discriminator can be used in place of a VAE’s decoder to learn the loss function. The motivation behind this modification is as mentioned above, VAEs tend to produce blurry outputs during the reconstruction phase. This “blurriness” is somehow related to the way VAE’s loss function is calculated.