A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1610.02136/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTA Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks — mentioned by nothing0001https://news.ycombinator.com/item?id=34676008urn:hackerpapers:mention:1610.02136:34676008Mon, 06 Feb 2023 11:31:07 GMT<p>Just make a loss function that gives +1 for correct answer, -1 for incorrect answers and 0 for unknown. Since this idea took me like 10 seconds, I suppose something like this must/should have been used before. Unrelated, what happen when we train a model using a discontinuous function? Could the trained model be used to detect some pattern in the data?, for example if the input vector to such a model is a direct sum of two independent variables could such model be used to detect that the problem can be decomposed in two independent problems. Sorry of being off-topic and thinking aloud.…</p><p><a href="https://hackerpaper.kaipfister.de/p/1610.02136/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.NE