https://hackerpaper.kaipfister.de/p/1901.11390/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=20076015urn:hackerpapers:mention:1901.11390:20076015Sun, 02 Jun 2019 15:21:11 GMT<p>It depends how those symbols are encoded. Techniques like attention, and systems like transformers that are built on top of them, are often produce highly interpretable execution traces simply because their patterns of activity are very revealing of how they are going about solving the task. It&#x27;s harder to interrogate their learned weights in any free-standing way, of course. But the neuro-symbolic concept learning paper I gave already shows the potential translucency of these kinds of hybrid systems: the linguistic interface (its a VQA task) allows one to simply look up the feature vectors…</p><p><a href="https://hackerpaper.kaipfister.de/p/1901.11390/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CVhttps://news.ycombinator.com/item?id=19060223urn:hackerpapers:submission:1901.11390:19060223Sat, 02 Feb 2019 00:57:31 GMT<p>[1901.11390] MONet: Unsupervised Scene Decomposition and Representation</p><p></p><p>3 points; 1 discussion reply on HN. <a href="https://hackerpaper.kaipfister.de/p/1901.11390/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CV