https://hackerpaper.kaipfister.de/p/2005.08926/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=23595275urn:hackerpapers:mention:2005.08926:23595275Sun, 21 Jun 2020 20:46:36 GMT<p>Was prepared for an introduction to some novel never-before-seen method near the end, but this was a nice and well-structured summary regardless! Wanted to tack on a couple of questions/thoughts: 1. Is the author familiar with all of the recent work around neural differential equations? Latent (Neural) ODEs[1] and Neural Controlled Differential Equations[2] are already able to match or exceed the performance of GRU-D when working with certain sparse and irregularly-sampled time series. 2. More of a nitpick, but most of the models covered as working with EHR data are using clinical data…</p><p><a href="https://hackerpaper.kaipfister.de/p/2005.08926/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG