https://hackerpaper.kaipfister.de/p/1808.05377/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=23072163urn:hackerpapers:submission:1808.05377:23072163Mon, 04 May 2020 19:20:25 GMT<p>Ask HN: Has anyone tried to search for new, basic machine learning operations?</p><p>E.g. primitive operations like convolution and pooling. From Neural Architecture Search: A Survey[0], first published in 2018: &quot;Moreover, common search spaces are also based on predefined building blocks, such as different kinds of convolutions and pooling, but do not allow identifying novel building blocks on this level; going beyond this limitation might substantially increase the power of NAS.&quot; I wonder now if somebody tried that since this was written or if anybody has some thoughts about the feasibility of this idea. We&#x27;ve been using these methods for years. I doubt the first few…</p><p>1 point; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1808.05377/">Paper and source history</a>. A submission is not an endorsement.</p>stat.ML