korrents

On the map

Tap a claim on the ring to put it at the centre.

← An adversarial GAN loss should only supplement a larger unsupervised…

8 connected korrents · 8 moments from 10 Jun 2014 to 24 Jun 2026.

Everything filed under GANs GANs Everything filed under neural networks neural networks Everything filed under scaling laws scaling laws Everything filed under design design Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: An adversarial GAN loss should only supplement a larger unsupervised or semi-supervised generative model rather than stand alone as a primary approach. An adversarial GAN loss should onlysupplement a larger unsupervised orsemi-supervised generative model ratherthan stand alone as a primary approach. Last stated 6 years ago 4 Feb 2021 GW Gwern — holds since 2021-02-04 — tap for who they are Same subject: Adversarial nets need neither Markov chains nor unrolled approximate inference networks for training or sample generation. — tap to centre the map on it Adversarial nets need neither Markovchains nor unrolled approximateinference networks for training orsample generation. Last stated 12 years ago 10 Jun 2014 YB Yoshua Bengio — holds since 2014-06-10 — tap for who they are Same subject: Generative AI has failed to produce the learning gains it was promised to deliver and instead shows evidence of harming learning. — tap to centre the map on it Generative AI has failed to producethe learning gains it was promisedto deliver and instead showsevidence of harming learning. Last stated 4 months ago 24 Jun 2026 DM Dan Meyer — holds since 2026-06-24 — tap for who they are Same subject: Deep generative models have had less impact than discriminative models because of intractable probabilistic computations and difficulty using piecewise linear units. — tap to centre the map on it Deep generative models have had lessimpact than discriminative modelsbecause of intractable probabilisticcomputations and difficulty usingpiecewise linear units. Last stated 12 years ago 10 Jun 2014 YB Yoshua Bengio — holds since 2014-06-10 — tap for who they are Same subject: Current techniques restrict pre-trained representation power because standard language models are unidirectional. — tap to centre the map on it Current techniques restrictpre-trained representation powerbecause standard language models areunidirectional. Last stated 8 years ago 11 Oct 2018 KT Kristina Toutanova — holds since 2018-10-11 — tap for who they are MC Ming-Wei Chang — holds since 2018-10-11 — tap for who they are KL Kenton Lee — holds since 2018-10-11 — tap for who they are JD Jacob Devlin — holds since 2018-10-11 — tap for who they are Same subject: We have almost no automated techniques for making a system transfer what it learns, and none of the few we have are used in modern deep learning. — tap to centre the map on it We have almost no automatedtechniques for making a systemtransfer what it learns, and none ofthe few we have are used in moderndeep learning. Last stated a year ago 26 Sept 2025 RS Richard Sutton — holds since 2025-09-26 — tap for who they are Same subject: Supervised pretraining on ImageNet is now obsolete for transfer learning, and ImageNet itself is just a contaminated validation set. — tap to centre the map on it Supervised pretraining on ImageNetis now obsolete for transferlearning, and ImageNet itself isjust a contaminated validation set. Last stated 6 years ago 6 Apr 2021 GW Gwern — holds since 2021-04-06 — tap for who they are Same subject: The knowledge a model soaks up in pre-training is holding it back; what we actually want is the intelligence with the knowledge stripped out. — tap to centre the map on it The knowledge a model soaks up inpre-training is holding it back;what we actually want is theintelligence with the knowledgestripped out. Last stated a year ago 17 Oct 2025 AK Andrej Karpathy — holds since 2025-10-17 — tap for who they are Same subject: RL environments exist to make a model generalise, not to teach it each skill one at a time — exactly as pre-training does. — tap to centre the map on it RL environments exist to make amodel generalise, not to teach iteach skill one at a time — exactlyas pre-training does. Last stated 8 months ago 13 Feb 2026 DA Dario Amodei — holds since 2026-02-13 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2014 to today (stretched back to the oldest claim here) — full is todaya face: someone who holds the claim — tap it for who they are

At the centre An adversarial GAN loss should only supplement a larger unsupervised or semi-supervised generative model rather than stand alone as a primary approach. Last stated 4 Feb 2021 · 6 years ago Holds Gwern Read this korrent →