https://hackerpaper.kaipfister.de/p/2006.04528/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=27862594urn:hackerpapers:mention:2006.04528:27862594Sat, 17 Jul 2021 00:17:46 GMT<p>Related to understanding how ML models are making their decisions is the concept of influence [1] (or broadly, instance based explanations) [2] where the training data that is most influential in a prediction (basically the analogy the model used) is highlighted. See also [3] where I provide a take on using these methods for understanding if you can trust a prediction or not, based on whether the model has an appropriate analogy to work from [1] Understanding black box predictions through influence functions, https://arxiv.org/abs/1703.04730 [2] Evaluation of Similarity-based Explanations…</p><p><a href="https://hackerpaper.kaipfister.de/p/2006.04528/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG