Scaling Forward Gradient With Local Losses · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2210.03310/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTScaling Forward Gradient With Local Losses — HN submissionhttps://news.ycombinator.com/item?id=36012319urn:hackerpapers:submission:2210.03310:36012319Sat, 20 May 2023 14:43:29 GMT<p>How to train deep neural networks without backprop</p><p></p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2210.03310/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGScaling Forward Gradient With Local Losses — mentioned by duvenaudhttps://news.ycombinator.com/item?id=34358940urn:hackerpapers:mention:2210.03310:34358940Thu, 12 Jan 2023 19:20:15 GMT<p>Perhaps a better place to find algorithmic details is this related paper, also with Hinton as a co-author, which implements similar ideas in more standard networks: Scaling Forward Gradient With Local Losses Mengye Ren, Simon Kornblith, Renjie Liao, Geoffrey Hinton https://arxiv.org/abs/2210.03310 and has code: https://github.com/google-research/google-research/tree/mast...</p><p><a href="https://hackerpaper.kaipfister.de/p/2210.03310/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG