Machine Learning Projects for Mobile Applications

Generative versus discriminative algorithms

To understand GANs, we should know how discriminative and generative algorithms work. Discriminative algorithms try to predict a label and classify the input data or categorize them to where the data belongs. On the other hand, generative algorithms attempt to predict features given a certain label.

For example, a discriminative algorithm could predict whether an email message is spam or not spam. Here, spam is one of the labels, and the text captured from the message is considered the input data. If you consider the label as y and input as x, we can formulate this as follows:

p(y|x)

This means the probability of y given x, which translates to the probability of an email is being spam given the ...