Deep Learning By Example

Intuition

When building a GAN for generating images, we trained both   the generator and the discriminator at the same time. After training, we can discard the discriminator because we only used it for training the generator.

Figure 6: Semi-supervised learning GAN architecture for an 11 class classification problem

In semi-supervised learning, we need to transform the discriminator into a multi-class classifier. This new model has to be able to generalize well on the test set, even though we do not have many labeled examples for training. Additionally, this time, by the end of training, we can actually throw away the generator. Note that ...