'/%3e%3cpath%20d='M50.3943%2022.237V39.5876H43.5185V22.7481C43.5185%2019.2029%2042.0411%2017.3949%2039.036%2017.3949C35.7325%2017.3949%2034.0778%2019.5338%2034.0778%2023.7585V32.9759H27.2434V23.7585C27.2434%2019.5338%2025.5857%2017.3949%2022.2822%2017.3949C19.2949%2017.3949%2017.8027%2019.2029%2017.8027%2022.7481V39.5876H10.9298V22.237C10.9298%2018.6918%2011.835%2015.8754%2013.6453%2013.7877C15.5128%2011.7049%2017.9623%2010.6355%2021.0028%2010.6355C24.522%2010.6355%2027.1813%2011.9885%2028.9542%2014.6917L30.665%2017.5633L32.3788%2014.6917C34.1517%2011.9885%2036.811%2010.6355%2040.3243%2010.6355C43.3619%2010.6355%2045.8114%2011.7049%2047.6847%2013.7877C49.4931%2015.8734%2050.3963%2018.6899%2050.3943%2022.237Z'%20fill='white'/%3e%3cdefs%3e%3clinearGradient%20id='paint0_linear_89_8'%20x1='30.5'%20y1='0'%20x2='30.5'%20y2='65'%20gradientUnits='userSpaceOnUse'%3e%3cstop%20stop-color='%236364FF'/%3e%3cstop%20offset='1'%20stop-color='%23563ACC'/%3e%3c/linearGradient%3e%3c/defs%3e%3c/svg%3e)
Charlotte Aten<p>By the way, you can see the poster I presented in 2017 here: <a href="https://aten.cool/documents/NCUWM_poster.pdf" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">aten.cool/documents/NCUWM_post</span><span class="invisible">er.pdf</span></a></p><p>This kind of idea appears in my work with Semin Yoo on constructing manifolds from quasigroups, so I'm still up to some of the same things seven years later.</p><p>Quasigroup manifolds paper: <a href="https://arxiv.org/abs/2110.05660" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2110.05660</span><span class="invisible"></span></a></p><p><a href="https://mathstodon.xyz/tags/algebra" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>algebra</span></a> <a href="https://mathstodon.xyz/tags/topology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>topology</span></a> <a href="https://mathstodon.xyz/tags/manifolds" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>manifolds</span></a> <a href="https://mathstodon.xyz/tags/UniversalAlgebra" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UniversalAlgebra</span></a> <a href="https://mathstodon.xyz/tags/combinatorics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>combinatorics</span></a></p>
101010.pl is one of the many independent Mastodon servers you can use to participate in the fediverse.
101010.pl czyli najstarszy polski serwer Mastodon. Posiadamy wpisy do 2048 znaków.
Administered by:
Server stats:
516active users
101010.pl: About · Status · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.0-beta.1
#manifolds
0 posts · 0 participants · 0 posts today
Giulio<p>Discussing slide 49/237 with <a href="https://mastodon.world/tags/chatgpt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>chatgpt</span></a> </p><p><a href="https://mastodon.world/tags/Embedded" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Embedded</span></a> vs <a href="https://mastodon.world/tags/Immersed" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Immersed</span></a> <a href="https://mastodon.world/tags/Manifolds" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Manifolds</span></a></p><p><a href="https://chat.openai.com/share/6cbf3e83-a52d-469e-8ea8-c003c06a1073" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">chat.openai.com/share/6cbf3e83</span><span class="invisible">-a52d-469e-8ea8-c003c06a1073</span></a></p><p>and with <a href="https://mastodon.world/tags/bard" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>bard</span></a> </p><p><a href="https://g.co/bard/share/f9fd23a81646" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">g.co/bard/share/f9fd23a81646</span><span class="invisible"></span></a></p>
Victoria Stuart 🇨🇦 🏳️⚧️<p>...<br>Addendae (cont'd)</p><p>Manifold hypothesis<br><a href="https://en.wikipedia.org/wiki/Manifold_hypothesis" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">en.wikipedia.org/wiki/Manifold</span><span class="invisible">_hypothesis</span></a></p><p>Many high-dimensional data sets (requiring many variables) in the real world actually lie along low-dimensional latent manifolds in that high-dimensional space (described by a smaller number of variables).</p><p>This principle may underpin the effectiveness of ML algorithms in describing high-dimensional data sets by considering a few common features.</p><p><a href="https://mastodon.social/tags/ManifoldHypothesis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ManifoldHypothesis</span></a> <a href="https://mastodon.social/tags/manifolds" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>manifolds</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/DimensionalityReduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DimensionalityReduction</span></a></p>
Victoria Stuart 🇨🇦 🏳️⚧️<p>On the curvature of the loss landscape<br><a href="https://arxiv.org/abs/2307.04719" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2307.04719</span><span class="invisible"></span></a></p><p>A main challenge in modern deep learning is to understand why such over-parameterized models perform so well when trained on finite data ... we consider the loss landscape as an embedded Riemannian manifold ... we focus on the scalar curvature, which can be computed analytically for our manifold ...</p><p>Manifolds: <a href="https://en.wikipedia.org/wiki/Manifold" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">en.wikipedia.org/wiki/Manifold</span><span class="invisible"></span></a><br>...</p><p><a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/NeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NeuralNetworks</span></a> <a href="https://mastodon.social/tags/manifolds" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>manifolds</span></a> <a href="https://mastodon.social/tags/parametrization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>parametrization</span></a> <a href="https://mastodon.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearning</span></a> <a href="https://mastodon.social/tags/LossFunctions" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LossFunctions</span></a></p>
Seth Axen 🪓 :julia:Introduction
Seth Axen 🪓<p>I just migrated from <span class="h-card"><a href="https://mastodon.social/@sethaxen" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>sethaxen@mastodon.social</span></a></span> to this new account at fosstodon.org, so time for a reintroduction!</p><p>I'm a <a href="https://fosstodon.org/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> engineer with a focus on probabilistic programming (<a href="https://fosstodon.org/tags/probprog" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>probprog</span></a>) at @unituebingen, where I help scientists use ML for their research. In the office and out, one of my main passions is <a href="https://fosstodon.org/tags/FOSS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FOSS</span></a>, and I work on a number of <a href="https://fosstodon.org/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> packages, mostly in <a href="https://fosstodon.org/tags/JuliaLang" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JuliaLang</span></a> :julia: with a focus on <a href="https://fosstodon.org/tags/probprog" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>probprog</span></a>, <a href="https://fosstodon.org/tags/manifolds" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>manifolds</span></a>, and <a href="https://fosstodon.org/tags/autodiff" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>autodiff</span></a>.</p><p><a href="https://fosstodon.org/tags/introduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>introduction</span></a></p>
Seth Axen 🪓<p>Hello fediverse!</p><p>I'm a <a href="https://mastodon.social/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> engineer with a focus on probabilistic programming (<a href="https://mastodon.social/tags/probprog" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>probprog</span></a>) at <span class="h-card"><a href="https://xn--baw-joa.social/@unituebingen" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>unituebingen</span></a></span>, where I help scientists use ML for their research. In the office and out, one of my main passions is <a href="https://mastodon.social/tags/FOSS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FOSS</span></a>, and I work on a number of <a href="https://mastodon.social/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> packages, mostly in <a href="https://mastodon.social/tags/JuliaLang" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>JuliaLang</span></a>, with a focus on <a href="https://mastodon.social/tags/probprog" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>probprog</span></a>, <a href="https://mastodon.social/tags/manifolds" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>manifolds</span></a>, and <a href="https://mastodon.social/tags/autodiff" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>autodiff</span></a>.</p><p>I have no idea what this account will be about, but probably some combination of the above topics. 👋</p><p><a href="https://mastodon.social/tags/introduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>introduction</span></a></p>
ExploreLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload