Harmonizing the object recognition strategies of deep neural networks with humans · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2211.04533/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTHarmonizing the object recognition strategies of deep neural networks with humans — mentioned by snaking0776https://news.ycombinator.com/item?id=47894984urn:hackerpapers:mention:2211.04533:47894984Fri, 24 Apr 2026 19:50:49 GMT<p>As someone actively researching in the neuroscience field these ideas are increasingly questionable. They do do a decent job of job of predicting neural data depending on your definition and if you compare them to hand built sets of features but we’re actually not even sure that will stay true. Especially in vision we already know that as models have scaled up they actually diverge more from humans and use quite different strategies. If you want them to act like humans or better reflect neural data you have to actively shape the training process to make that happen. There’s less we know about…</p><p><a href="https://hackerpaper.kaipfister.de/p/2211.04533/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CV