https://hackerpaper.kaipfister.de/p/2001.05016/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=30915831urn:hackerpapers:mention:2001.05016:30915831Tue, 05 Apr 2022 06:15:55 GMT<p>Really? Better inform all the researchers working on this that they&#x27;re wasting their time then: https://arxiv.org/abs/2001.05016 More fundamentally, any finite neural net is either constant or linear outside the training sample,depending on the activation function. Unless you design special neurons like in the paper above, which solves this specific problem for arithmetic, but not the general problem of extrapolation.</p><p><a href="https://hackerpaper.kaipfister.de/p/2001.05016/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.NE