Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Why can Generative Adversarial Networks (GANs) learn any probability distribution function (pdf)?

9 minute read

Published:

This is somewhat a work in progress post… In this post, I will talk about the ability of GANs to learn a probability density function (pdf). A pdf is used to specify the probability of the random variable falling within a particular range of values. For example, consider the amount of euros/dollars you spend on groceries each month (random variable). For one individual, this will just be one value (e.g., 200 euros) but now consider the montly spending on groceries of all the individuals in the Netherlands. This can be summarized efficiently with a pdf (the red line):

portfolio

publications

talks

teaching