Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1910.12478/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTTensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes — HN submissionhttps://news.ycombinator.com/item?id=21651113urn:hackerpapers:submission:1910.12478:21651113Wed, 27 Nov 2019 19:28:55 GMT<p>Wide Neural Networks of Any Architecture Are Gaussian Processes</p><p></p><p>144 points; 34 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1910.12478/">Paper and source history</a>. A submission is not an endorsement.</p>cs.NE