Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation? · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2202.09467/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTPredictive Coding: Towards a Future of Deep Learning beyond Backpropagation? — mentioned by Piezoidhttps://news.ycombinator.com/item?id=35685408urn:hackerpapers:mention:2202.09467:35685408Mon, 24 Apr 2023 09:31:31 GMT<p>In neuroscience, predictive coding [1] is a theory that proposes the brain makes predictions about incoming sensory information and adjusts them based on any discrepancies between the predicted and actual sensory input. It involves simultaneous learning and inference, and there is some research [2] that suggests it is related to back-propagation. Given that large language models perform some kind of implicit gradient descent during in-context learning, it raises the question of whether they are also doing some form of predictive coding. If so, could this provide insights on how to better…</p><p><a href="https://hackerpaper.kaipfister.de/p/2202.09467/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.NE