Noise-trained deep neural networks effectively predict human vision and its neural responses to challenging images.

PLoS Biol · 2021 · PMC8659651 · PMID 34882676

Europe PMC DOI

hedged sentence

0.0000

closest p · 0.0× alpha

0.0000

boldest claim

The sentences

highly significantp < 10 −14actually significant

This analysis confirmed that human observers exhibited much lower SSNR thresholds than DNNs, outperforming the DNNs by a highly significant margin at recognizing objects in pixelated noise ( t (26) = 15.94, p < 10 −14 ); they also outperformed DNNs at recognizing objects in Fourier phase-scrambled noise ( t (26) = 12.29, p < 10 −11 ).

also in 132,142 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.