RSS

GAN

TagLast edit: Feb 5, 2021, 6:17 PM by plex

Generative Adversarial Network is a machine learning architecture containing two modules. The generator attempts to create an output that is similar to the network’s training data, while the discriminator attempts to tell the generator’s outputs apart from the training data. The generator is reinforced based on how well its outputs fool the discriminator, so the two modules are adversaries.

GANs are best known for working well with images; for example, generating pictures of human faces.

Google’s new text-to-image model—Parti, a demon­stra­tion of scal­ing benefits

KaydenJun 22, 2022, 8:00 PM
32 points
4 comments1 min readLW link

GAN Discrim­i­na­tors Don’t Gen­er­al­ize?

tryactionsJun 8, 2020, 8:36 PM
18 points
7 comments2 min readLW link

Gen­er­a­tive ad­ver­sar­ial mod­els, in­formed by arguments

jessicataJun 27, 2016, 7:28 PM
0 points
0 comments2 min readLW link

[Question] GPT-3 + GAN

stick109Oct 17, 2020, 7:58 AM
4 points
3 comments1 min readLW link

Can you force a neu­ral net­work to keep gen­er­al­iz­ing?

Q HomeSep 12, 2022, 10:14 AM
2 points
10 comments5 min readLW link

Digi­tal Molec­u­lar Assem­blers: What syn­thetic me­dia/​gen­er­a­tive AI ac­tu­ally rep­re­sents, and where I think it’s going

Yuli_BanFeb 28, 2023, 2:03 PM
26 points
4 comments15 min readLW link

Steganog­ra­phy and the Cy­cleGAN—al­ign­ment failure case study

Jan CzechowskiJun 11, 2022, 9:41 AM
34 points
0 comments4 min readLW link
No comments.