What Yoshua Bengio thinks about GANs

@yoshua-bengio · 24 positions · 1 change of mind · On ppll ↗

Deep-learning researcher and Turing Award laureate; founder of the Mila institute.

Yoshua Bengio did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter GANs · Newest first

Topic

All 24AI alignment 13neural networks 6computer vision 3AGI 2LLMs 2agency 1aviation 1energy 1GANs 1

4 more topics

government 1nuclear power 1open source 1war 1

Sort

NewestOldest

Only Yoshua Bengio on GANs. See everyone on GANs

1 dated position, 2014, in their own words. Our reading of what Yoshua Bengio has said — not written or endorsed by them.

1 position so far — this page is not yet offered to search engines.

1. 10 Jun 2014

   Our readingAdversarial nets need neither Markov chains nor unrolled approximate inference networks for training or sample generation.

   Their wordsThere is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples.

   ↗Generative Adversarial Networks (with 7 co-authors)arxiv.org All 2 from this paper