Online Spatio-Temporal Learning in Deep Neural Networks · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2007.12723/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTOnline Spatio-Temporal Learning in Deep Neural Networks — mentioned by orbifoldhttps://news.ycombinator.com/item?id=24695993urn:hackerpapers:mention:2007.12723:24695993Tue, 06 Oct 2020 09:20:36 GMT<p>They don&#x27;t address the fundamental issue of BPTT in an RNN model. To my mind this is a much larger block to biological plausibility than how to track the error locally. Besides this has been addressed in various forms in earlier work: - Hochreiter and Schmidhuber present a truncated version of BPTT in the original LSTM paper that tracks part of the error locally and forward in time (https://www.bioinf.jku.at/publications/older/2604.pdf) - Bellec et al. https://www.nature.com/articles/s41467-020-17236-y present a similar algorithm that tracks the error with something they call eligibility…</p><p><a href="https://hackerpaper.kaipfister.de/p/2007.12723/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG