sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Server stats:

599
active users

#continuallearning

0 posts0 participants0 posts today
Victor Paléologue<p>As they present their idea for producing symbolic AI domains using <a href="https://fediscience.org/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a>, they present an interesting summary of why "Good Old-Fashioned <a href="https://fediscience.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a>" is still totally relevant today - despite being aware of its limitations.</p><p><a href="https://www.youtube.com/watch?v=_TrKARhF5cI" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=_TrKARhF5c</span><span class="invisible">I</span></a></p><p>I, too, rather recommend traditional <a href="https://fediscience.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> in my solutions, instead of blindly yielding to the current trends.</p><p>Plus it paves the way for <a href="https://fediscience.org/tags/continuallearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>continuallearning</span></a> to improve the skills with time.</p>
Lukas Galke<p>I&#39;m so excited for the Unconference :) It just started but you can still register/join.</p><p><a href="https://unconf.continualai.org/register" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">unconf.continualai.org/register</span><span class="invisible"></span></a></p><p><a href="https://sigmoid.social/tags/unconf23" class="mention hashtag" rel="tag">#<span>unconf23</span></a> <a href="https://sigmoid.social/tags/ContinualLearning" class="mention hashtag" rel="tag">#<span>ContinualLearning</span></a> <a href="https://sigmoid.social/tags/LifelongLearning" class="mention hashtag" rel="tag">#<span>LifelongLearning</span></a> <a href="https://sigmoid.social/tags/MachineLearning" class="mention hashtag" rel="tag">#<span>MachineLearning</span></a></p>
Gido van de Ven<p>The paper submission deadline for the CLVision workshop has been extended to March 13th.</p><p>There is still time to submit your (archival or non-archival) contribution!</p><p><a href="https://sigmoid.social/tags/CVPR" class="mention hashtag" rel="tag">#<span>CVPR</span></a> <a href="https://sigmoid.social/tags/continuallearning" class="mention hashtag" rel="tag">#<span>continuallearning</span></a></p>
Gido van de Ven<p>The challenge for the CLVision workshop is announced! <a href="https://sigmoid.social/tags/continuallearning" class="mention hashtag" rel="tag">#<span>continuallearning</span></a> <a href="https://sigmoid.social/tags/CVPR2023" class="mention hashtag" rel="tag">#<span>CVPR2023</span></a></p><p>Can you design a strategy to efficiently leverage repetition in continual learning streams?</p><p>Read more on the website, and be ready when the challenge starts (20 March)!</p><p><a href="https://sites.google.com/view/clvision2023/challenge" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">sites.google.com/view/clvision</span><span class="invisible">2023/challenge</span></a></p>
Max Vladymyrov 🇺🇦<p>ML algorithms need lots of data and are prone to catastrophic forgetting. We present a new method for continual few-shot learning, bringing us closer to the way humans learn: sample efficient, while maintaining long-term retention.<br />📜<a href="https://arxiv.org/abs/2301.04584" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">arxiv.org/abs/2301.04584</span><span class="invisible"></span></a></p><p>🧵 below:</p><p><a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="tag">#<span>AI</span></a> <a href="https://sigmoid.social/tags/CV" class="mention hashtag" rel="tag">#<span>CV</span></a> <a href="https://sigmoid.social/tags/NewPaper" class="mention hashtag" rel="tag">#<span>NewPaper</span></a> <a href="https://sigmoid.social/tags/DeepLearning" class="mention hashtag" rel="tag">#<span>DeepLearning</span></a> <a href="https://sigmoid.social/tags/MachineLearning" class="mention hashtag" rel="tag">#<span>MachineLearning</span></a> <a href="https://sigmoid.social/tags/FewShotLearning" class="mention hashtag" rel="tag">#<span>FewShotLearning</span></a> <a href="https://sigmoid.social/tags/ContinualLearning" class="mention hashtag" rel="tag">#<span>ContinualLearning</span></a> <a href="https://sigmoid.social/tags/HyperNetworks" class="mention hashtag" rel="tag">#<span>HyperNetworks</span></a> <a href="https://sigmoid.social/tags/Transformers" class="mention hashtag" rel="tag">#<span>Transformers</span></a></p>
Cédric Archambeau<p>Another day another launch 😬<br />I am super excited to announce that we open sourced Renate, a <a href="https://sigmoid.social/tags/ContinualLearning" class="mention hashtag" rel="tag">#<span>ContinualLearning</span></a> library to automatically retrain and retune deep neural networks.<br /><a href="https://sigmoid.social/tags/deeplearning" class="mention hashtag" rel="tag">#<span>deeplearning</span></a> <a href="https://sigmoid.social/tags/opensource" class="mention hashtag" rel="tag">#<span>opensource</span></a> <a href="https://sigmoid.social/tags/aws" class="mention hashtag" rel="tag">#<span>aws</span></a></p><p><a href="https://github.com/awslabs/Renate" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">github.com/awslabs/Renate</span><span class="invisible"></span></a></p>
Sanket Vaibhav Mehta<p><a href="https://sigmoid.social/tags/Introduction" class="mention hashtag" rel="tag">#<span>Introduction</span></a> I&#39;m a <a href="https://sigmoid.social/tags/PhD" class="mention hashtag" rel="tag">#<span>PhD</span></a> student at <a href="https://sigmoid.social/tags/LTI" class="mention hashtag" rel="tag">#<span>LTI</span></a> <a href="https://sigmoid.social/tags/SCS" class="mention hashtag" rel="tag">#<span>SCS</span></a> <a href="https://sigmoid.social/tags/CMU" class="mention hashtag" rel="tag">#<span>CMU</span></a></p><p>I&#39;m interested in <a href="https://sigmoid.social/tags/ML" class="mention hashtag" rel="tag">#<span>ML</span></a> <a href="https://sigmoid.social/tags/NLP" class="mention hashtag" rel="tag">#<span>NLP</span></a> and <a href="https://sigmoid.social/tags/Optimization" class="mention hashtag" rel="tag">#<span>Optimization</span></a> with a specific focus on <a href="https://sigmoid.social/tags/LifelongLearning" class="mention hashtag" rel="tag">#<span>LifelongLearning</span></a> <a href="https://sigmoid.social/tags/ContinualLearning" class="mention hashtag" rel="tag">#<span>ContinualLearning</span></a> <a href="https://sigmoid.social/tags/MetaLearning" class="mention hashtag" rel="tag">#<span>MetaLearning</span></a> and <a href="https://sigmoid.social/tags/MultitaskLearning" class="mention hashtag" rel="tag">#<span>MultitaskLearning</span></a></p>
Gido van de Ven<p>Another <a href="https://sigmoid.social/tags/CLVision" class="mention hashtag" rel="tag">#<span>CLVision</span></a> (Continual Learning in Computer Vision) workshop at <a href="https://sigmoid.social/tags/CVPR2023" class="mention hashtag" rel="tag">#<span>CVPR2023</span></a> coming up. The 4th edition! 🥳 🎉 </p><p>More details, invited speakers and the call for papers will be announced early January. Stay tuned! <a href="https://sigmoid.social/tags/continuallearning" class="mention hashtag" rel="tag">#<span>continuallearning</span></a></p><p><a href="https://sites.google.com/view/clvision2023" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">sites.google.com/view/clvision</span><span class="invisible">2023</span></a></p>
Tom Diethe<p>Hi all. First post on here. In case you don’t know me, I’ve been in <a href="https://sigmoid.social/tags/machinelearning" class="mention hashtag" rel="tag">#<span>machinelearning</span></a> for a while (trained my first <a href="https://sigmoid.social/tags/neural" class="mention hashtag" rel="tag">#<span>neural</span></a> networks in 1999, but they were rubbish!) now focused on <a href="https://sigmoid.social/tags/compBio" class="mention hashtag" rel="tag">#<span>compBio</span></a> applications (mainly <a href="https://sigmoid.social/tags/proteinengineering" class="mention hashtag" rel="tag">#<span>proteinengineering</span></a> ), but also interests in <a href="https://sigmoid.social/tags/bayesian" class="mention hashtag" rel="tag">#<span>bayesian</span></a> statistics, <a href="https://sigmoid.social/tags/PrivacyEnhancingTechnologies" class="mention hashtag" rel="tag">#<span>PrivacyEnhancingTechnologies</span></a> and <a href="https://sigmoid.social/tags/continuallearning" class="mention hashtag" rel="tag">#<span>continuallearning</span></a> . Currently leading a fantastic team of scientists and engineers at Amazon. Slightly sad at the demise of Twitter, hoping <a href="https://sigmoid.social/tags/mastodon" class="mention hashtag" rel="tag">#<span>mastodon</span></a> can fill the hole it left!</p>
Eugenio Culurciello<p>Drop the dataset! <br />It has hindered our progress in machine learning and it si time to go beyond!<br /><a href="https://culurciello.medium.com/drop-the-dataset-b3ed418bd69d" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">culurciello.medium.com/drop-th</span><span class="invisible">e-dataset-b3ed418bd69d</span></a><br /><a href="https://sigmoid.social/tags/deeplearning" class="mention hashtag" rel="tag">#<span>deeplearning</span></a> <a href="https://sigmoid.social/tags/ai" class="mention hashtag" rel="tag">#<span>ai</span></a> <a href="https://sigmoid.social/tags/machinelearning" class="mention hashtag" rel="tag">#<span>machinelearning</span></a> <a href="https://sigmoid.social/tags/unsupervisedlearning" class="mention hashtag" rel="tag">#<span>unsupervisedlearning</span></a> <a href="https://sigmoid.social/tags/continuallearning" class="mention hashtag" rel="tag">#<span>continuallearning</span></a></p>
Julian Elve<p>Obligatory <a href="https://social.synesthesia.co.uk/tags/Introduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Introduction</span></a> post</p><p>Technology strategy, data protection, business applications (<a href="https://social.synesthesia.co.uk/tags/CSharp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CSharp</span></a> / <a href="https://social.synesthesia.co.uk/tags/PowerPlatform" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PowerPlatform</span></a> / <a href="https://social.synesthesia.co.uk/tags/Dynamics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Dynamics</span></a>).</p><p><a href="https://social.synesthesia.co.uk/tags/IndieWeb" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>IndieWeb</span></a> <a href="https://social.synesthesia.co.uk/tags/Blogging" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Blogging</span></a></p><p><a href="https://social.synesthesia.co.uk/tags/Education" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Education</span></a> <a href="https://social.synesthesia.co.uk/tags/UkPolitics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UkPolitics</span></a></p><p><a href="https://social.synesthesia.co.uk/tags/Programming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Programming</span></a> <a href="https://social.synesthesia.co.uk/tags/CTO" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CTO</span></a> <a href="https://social.synesthesia.co.uk/tags/InfoSec" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>InfoSec</span></a> <br><a href="https://social.synesthesia.co.uk/tags/ContinualLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ContinualLearning</span></a> <a href="https://social.synesthesia.co.uk/tags/KnowlegeManagement" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>KnowlegeManagement</span></a> <a href="https://social.synesthesia.co.uk/tags/PKM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PKM</span></a> <br><a href="https://social.synesthesia.co.uk/tags/ToolsForThought" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ToolsForThought</span></a>
</p><p>I blog at <a href="https://www.synesthesia.co.uk" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="">synesthesia.co.uk</span><span class="invisible"></span></a></p>