Efficiently applying attention to sequential data with the Recurrent Discounted Attention unit ยท HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1705.08480/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTEfficiently applying attention to sequential data with the Recurrent Discounted Attention unit โ€” HN submissionhttps://news.ycombinator.com/item?id=17197796urn:hackerpapers:submission:1705.08480:17197796Thu, 31 May 2018 16:45:56 GMT<p>Recurrent neural network with learnable attention span</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1705.08480/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGEfficiently applying attention to sequential data with the Recurrent Discounted Attention unit โ€” HN submissionhttps://news.ycombinator.com/item?id=17104648urn:hackerpapers:submission:1705.08480:17104648Fri, 18 May 2018 20:20:30 GMT<p>Recursive neural attention mechanism with forget gate</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1705.08480/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LGEfficiently applying attention to sequential data with the Recurrent Discounted Attention unit โ€” HN submissionhttps://news.ycombinator.com/item?id=15570621urn:hackerpapers:submission:1705.08480:15570621Fri, 27 Oct 2017 17:48:00 GMT<p>Recurrent Discount Unit</p><p></p><p>3 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1705.08480/">Paper and source history</a>. A submission is not an endorsement.</p>cs.LG