https://hackerpaper.kaipfister.de/p/2102.12627/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=26432397urn:hackerpapers:mention:2102.12627:26432397Fri, 12 Mar 2021 05:08:23 GMT<p>Self-supervised learning is very promising. But it is strange to me that so much computer vision research has no mention of the 3d structure of objects. That&#x27;s why I like things like this https://arxiv.org/abs/2102.12627 &quot;How to represent part-whole hierarchies in a neural network&quot; by Hinton.</p><p><a href="https://hackerpaper.kaipfister.de/p/2102.12627/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=26295036urn:hackerpapers:submission:2102.12627:26295036Sun, 28 Feb 2021 17:28:35 GMT<p>“This paper does not describe a working system.”</p><p></p><p>4 points; 2 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2102.12627/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=26285231urn:hackerpapers:submission:2102.12627:26285231Sat, 27 Feb 2021 14:59:22 GMT<p>How to represent part-whole hierarchies in a neural network</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2102.12627/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=26275572urn:hackerpapers:submission:2102.12627:26275572Fri, 26 Feb 2021 15:17:05 GMT<p>How to represent part-whole hierarchies in a neural network by Geoffrey Hinton</p><p></p><p>6 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2102.12627/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=26272198urn:hackerpapers:submission:2102.12627:26272198Fri, 26 Feb 2021 07:29:50 GMT<p>Ask HN: Has Geoffrey Hinton Solved AGI?</p><p>My friend sent me a link to Hinton&#x27;s latest paper &quot;How to represent part-whole hierarchies in a neural network&quot;[0]. He sent it to me with the caption, &quot;Hinton has solved AGI&quot;. How valid is that statement? [0]:https://arxiv.org/abs/2102.12627</p><p>1 point; 4 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2102.12627/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=26270668urn:hackerpapers:submission:2102.12627:26270668Fri, 26 Feb 2021 01:55:56 GMT<p>Geoff Hinton 2021 – How to represent part-whole hierarchies in a neural network</p><p></p><p>8 points; 2 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2102.12627/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CV