https://hackerpaper.kaipfister.de/p/1611.09827/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=13107349urn:hackerpapers:mention:1611.09827:13107349Mon, 05 Dec 2016 17:41:11 GMT<p>Hi savanaly, When we talk about &quot;what makes Bach sound like Bach,&quot; the technical concept we have in mind is the recent work in computer vision on style transfer. For example, https://arxiv.org/abs/1508.06576 We are excited to work on adapting these models to the musical domain! As for note prediction, you can see our results in our paper: https://arxiv.org/abs/1611.09827 Our are results for simple (2-layer, not very &quot;deep&quot; models); we were interested in understanding the low-level &quot;features&quot; of music rather than building a model that maximizes performance. Nevertheless, the results are quite…</p><p><a href="https://hackerpaper.kaipfister.de/p/1611.09827/">Paper and discussion history</a>. A mention is not an endorsement.</p>stat.ML