GANS: How machines convert data to images

Runs 21:20

Rob Miles is a Ph.D. student in computer science and a YouTuber about AI. In this video he walks through the processes involved in Generative Adversarial Networks (GANS).

A lot of AI activity involves classifying, for example letters, images, or sounds that are alike. Very simply, a machine learning system receives new data and compares it with known data. For example, a new image of a cat is compared with many thousands of images that include cats. When there is a sufficiently high probability for match, the algorithm determines it has identified something called ‘a cat’.

All of these images came from a GANS system, part of the bigGANS project

But how can machines form entirely new things; new images, words, sounds? There is a lot emerging in this area with a new system known as GANS, otherwise known as Generative Adversarial Networks (GANS).

OUR TAKE

  • GANS seems as if it will become increasingly important as its technology matures.
  • This is the clearest explanation of how it works that we’ve found, which is why we included as part of our collection of primer materials.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.