Skip to content

← All Q&A

How do Generative Adversarial Networks make deepfakes more realistic?

AI Product

Drawn from Lutz Finger's Forbes column, LinkedIn writing, and Cornell teaching. Sources are cited inline so you can read the originals.

Two competing neural networks train each other to create realistic fakes.

Generative Adversarial Networks, or GANs, were introduced in a 2014 academic study by Goodfellow and colleagues. GANs set up two neural networks to compete against each other. The first network, a generative neural network, creates a realistic image from a random seed through decoding. The second, a discriminative classifier, checks whether the image is real or fake. Through this competition, the two neural networks train each other and become more and more realistic over time. This architecture reinvigorated interest in deepfakes.

Overview Of How To Create Deepfakes - It’s Scarily Simple · Forbes


Have a follow-up? hello@lutzfinger.com. Or pick another question: all Q&A →