Explore Courses Blog Tutorials Interview Questions
0 votes
in Machine Learning by (19k points)
I hear from some sources that Generative adversarial networks are unsupervised ML, but i dont get it. Are Generative adversarial networks not in fact supervised?

1) 2-class case Real-against-Fake

Indeed one has to supply training data to the discriminator and this has to be "real" data, meaning data which i would label with f.e. 1. Even though one doesnt label the data explicit, one does so implicitly by presenting the discriminator in the first steps with training data, which you tell the discriminator is authentic. In that way you somehow tell the discriminator a labeling of the training data. And on the contrary a labeling of the noise data that is generated at the first steps of the generator, which the generator knows to be unauthentic.

2) Multi-class case

But it gets really strange in the multi class case. One has to supply descriptions in the training data. The obvious contradiction is that one supplies a response to an unsupervised ML algorithm.

1 Answer

0 votes
by (33.1k points)

GANs are unsupervised learning algorithms. They use the supervised loss as part of the training.

We know supervised learning is used to predict a label associated with the data. The goal is for the model to generalize new data.

In the GAN case, we don't need either of these components. The data comes in with no labels, and we are not trying to generalize any kind of prediction to new data. The goal is for the GAN to model how the data looks like, and be able to generate new examples of what we learned.

You can use a supervised component for an unsupervised task that is not particularly new. Random Forests have done this for a long time for outlier detection and the One-Class SVM for outlier detection is technically trained in supervised fashion with the original data being the real class and a single point at the origin of the space treated as the outlier class.

Hope this answer helps you! Machine Learning Algorithms, thus will be required for every domain for a better perception of SVM Algorithms.

Browse Categories