On the choice of metric in gradient-based theories of brain function ยท HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1805.11851/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTOn the choice of metric in gradient-based theories of brain function โ€” mentioned by jimfleminghttps://news.ycombinator.com/item?id=17279117urn:hackerpapers:mention:1805.11851:17279117Sun, 10 Jun 2018 17:28:06 GMT<p>The previous version has a PDF[0] but you&#x27;re right, the current version shows none. [0] https://arxiv.org/pdf/1805.11851v1.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/1805.11851/">Paper and discussion history</a>. A mention is not an endorsement.</p>q-bio.NCOn the choice of metric in gradient-based theories of brain function โ€” HN submissionhttps://news.ycombinator.com/item?id=17278530urn:hackerpapers:submission:1805.11851:17278530Sun, 10 Jun 2018 15:25:40 GMT<p>The limitations of gradient descent as a principle of brain function</p><p></p><p>119 points; 15 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1805.11851/">Paper and source history</a>. A submission is not an endorsement.</p>q-bio.NCOn the choice of metric in gradient-based theories of brain function โ€” HN submissionhttps://news.ycombinator.com/item?id=17273421urn:hackerpapers:submission:1805.11851:17273421Sat, 09 Jun 2018 15:17:56 GMT<p>The limitations of gradient descent as a principle of brain function</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1805.11851/">Paper and source history</a>. A submission is not an endorsement.</p>q-bio.NC