korrents

Our readingWhat is a korrent?

An adversarial GAN loss should only supplement a larger unsupervised or semi-supervised generative model rather than stand alone as a primary approach.

Drawn from what Gwern said

GANs
What this subject means

GANs Two networks trained against each other, one generating fake examples and one judging them, until the generator's output is convincing.

What Gwern actually said

  1. Gwern Pseudonymous essayist
    To take the GAN/DRL analogy seriously, perhaps they were they ultimately a dead end, akin to trying to learn everything from rewards, and an adversarial GAN loss ought to be only the cherry on the cake of a large unsupervised/semi-supervised generative model.

Added to korrents 25 Sept 2026 · How quotes work · Something wrong? Tell us

Do you hold this korrent?Do you also believe this?

I hold this too

Related korrents

Shared subject first, then similar wording. They may agree or disagree.

See this claim on the map