mathstodon.xyz is one of the many independent Mastodon servers you can use to participate in the fediverse.
A Mastodon instance for maths people. We have LaTeX rendering in the web interface!

Server stats:

2.8K
active users

#bayesiandeeplearning

0 posts0 participants0 posts today
Pierre-Simon Laplace<p>What if AI could know when it doesn’t know?</p><p>🎙️ Alex Andorra talks with Vincent Fortuin about Bayesian deep learning—why it matters for uncertainty, calibration, and real-world reliability.</p><p>🎧 Tune in: <a href="https://learnbayesstats.com/episode/129-bayesian-deep-learning-ai-for-science-vincent-fortuin" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">learnbayesstats.com/episode/12</span><span class="invisible">9-bayesian-deep-learning-ai-for-science-vincent-fortuin</span></a></p><p><a href="https://mstdn.science/tags/BayesianDeepLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>BayesianDeepLearning</span></a> <a href="https://mstdn.science/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://mstdn.science/tags/ReliableAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ReliableAI</span></a> <a href="https://mstdn.science/tags/AIResearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AIResearch</span></a></p>
UKP Lab<p>🤔 Variational learning is often thought to be impractical<br>🔥 Plot twist: it actually works better than Adam!</p><p>Meet IVON, a new optimizer that brings the best out of variational learning – 🧵 (1/9)</p><p>📰 <a href="https://arxiv.org/abs/2402.17641" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2402.17641</span><span class="invisible"></span></a></p><p><a href="https://sigmoid.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLProc</span></a> <a href="https://sigmoid.social/tags/ICML2024" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ICML2024</span></a> <a href="https://sigmoid.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DeepLearning</span></a> <a href="https://sigmoid.social/tags/VariationalLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VariationalLearning</span></a> <a href="https://sigmoid.social/tags/BayesianDeepLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>BayesianDeepLearning</span></a></p>