About us
Stay in touch
Generative adversarial networks, introduced by Ian Goodfellow and colleagues in 2014: two neural networks trained against each other, one making images and one judging them against real examples. They drove much of AI art between 2015 and 2021.
A lot of how I personally got to GANs was assuming that it would just not be economically viable to train the kinds of models that we have today.
Ian Goodfellow, Ian Goodfellow on Inventing GANs
For me, engaging with GANs feels different. I think they're an alternative narrative of how AI could happen, of how AI could evolve, where instead of moving in the direction of general models, you're moving in the direction of smaller, more specialized models.
Linda Dounia, Linda Dounia on Memory Machines