PLOS Biology<p>How does the <a href="https://fediscience.org/tags/brain" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>brain</span></a> transfer <a href="https://fediscience.org/tags/MotorSkills" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MotorSkills</span></a> between hands? This study reveals that transfer relies on re-expressing the neural patterns established during initial learning in distributed higher-order brain areas, offering new insights into learning <a href="https://fediscience.org/tags/generalization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generalization</span></a> <span class="h-card" translate="no"><a href="https://fediscience.org/@PLOSBiology" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>PLOSBiology</span></a></span> <a href="https://plos.io/41LOAWf" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">plos.io/41LOAWf</span><span class="invisible"></span></a></p>
eupolicy.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
This Mastodon server is a friendly and respectful discussion space for people working in areas related to EU policy. When you request to create an account, please tell us something about you.
Administered by:
Server stats:
206active users
eupolicy.social: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.3
#generalization
0 posts · 0 participants · 0 posts today
PLOS Biology<p>Humans can apply solutions of past problems to new problems. <span class="h-card" translate="no"><a href="https://fediscience.org/@gershbrain" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>gershbrain</span></a></span> <span class="h-card" translate="no"><a href="https://mastodon.online/@nicoschuck" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>nicoschuck</span></a></span> &co reveal the neural correlates of <a href="https://fediscience.org/tags/generalization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generalization</span></a> and show that humans apply past policies in a reward-sensitive manner that leads to high performance <span class="h-card" translate="no"><a href="https://fediscience.org/@PLOSBiology" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>PLOSBiology</span></a></span> <a href="https://plos.io/3SJPMof" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">plos.io/3SJPMof</span><span class="invisible"></span></a></p>
Jan Vlug<p><span class="h-card" translate="no"><a href="https://mastodon.social/@schizanon" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>schizanon</span></a></span> <span class="h-card" translate="no"><a href="https://en.osm.town/@strebski" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>strebski</span></a></span> <span class="h-card" translate="no"><a href="https://chaos.social/@fossdd" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>fossdd</span></a></span> I think <a href="https://mastodon.social/tags/nationalism" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nationalism</span></a> and <a href="https://mastodon.social/tags/generalization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generalization</span></a> are important factors for war and killing. I try to treat living beings as <a href="https://mastodon.social/tags/individuals" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>individuals</span></a>.</p>
Jess Thompson<p>Pleased to share my latest research "Zero-shot counting with a dual-stream neural network model" about a glimpsing neural network model that learns visual structure (here, number) in a way that generalises to new visual contents. The model replicates several neural and behavioural hallmarks of numerical cognition. </p><p><a href="https://neuromatch.social/tags/neuralnetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuralnetworks</span></a> <a href="https://neuromatch.social/tags/cognition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cognition</span></a> <a href="https://neuromatch.social/tags/neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuroscience</span></a> <a href="https://neuromatch.social/tags/generalization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generalization</span></a> <a href="https://neuromatch.social/tags/vision" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>vision</span></a> <a href="https://neuromatch.social/tags/enactivism" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>enactivism</span></a> <a href="https://neuromatch.social/tags/enactiveCognition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>enactiveCognition</span></a> <a href="https://neuromatch.social/tags/cognitivescience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cognitivescience</span></a> <a href="https://neuromatch.social/tags/CognitiveNeuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CognitiveNeuroscience</span></a> <a href="https://neuromatch.social/tags/computationalneuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computationalneuroscience</span></a> </p><p><a href="https://arxiv.org/abs/2405.09953" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2405.09953</span><span class="invisible"></span></a></p>
Erik Jonker<p>Sometimes I read an article twice, this was such an article, explains why also in 2024 we don't fully understand LLMs , they are not "just statistics" as some argue, simply because some aspects with regard to generalisation and over fitting seem to work differently. Working on those models is still "more alchemy then chemistry".<br><a href="https://www.technologyreview.com/2024/03/04/1089403/large-language-models-amazing-but-nobody-knows-why/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">technologyreview.com/2024/03/0</span><span class="invisible">4/1089403/large-language-models-amazing-but-nobody-knows-why/</span></a><br><a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://mastodon.social/tags/generativeAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generativeAI</span></a> <a href="https://mastodon.social/tags/statistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>statistics</span></a> <a href="https://mastodon.social/tags/generalization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generalization</span></a></p>
Johannes Lotz<p>Our <a href="https://scholar.social/tags/Tissue_Concepts" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tissue_Concepts</span></a> model scored second at the <a href="https://scholar.social/tags/SemiCol" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SemiCol</span></a> challenge on detection and segmentation of colorectal cancer! 🥳 Over a year ago, we started to work on a <a href="https://scholar.social/tags/multitask" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>multitask</span></a> learning pipeline aimed at small datasets and <a href="https://scholar.social/tags/generalization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generalization</span></a>. In SemiCol, it detected almost all cancer (AUC 0.997) in external data. </p><p>Congrats to the whole team at <a href="https://scholar.social/tags/Fraunhofer" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Fraunhofer</span></a> MEVIS and <br>many thanks to the organizers!<br><a href="https://scholar.social/tags/foundationmodels" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>foundationmodels</span></a> <a href="https://scholar.social/tags/digitalpathology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>digitalpathology</span></a> <a href="https://scholar.social/tags/ecdp2023" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ecdp2023</span></a></p>
Mircea<p><a href="https://masto.ai/tags/Introdiction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Introdiction</span></a> : I'm a mathematician moving towards data science topics, based in Chile. Some interests:<br><a href="https://masto.ai/tags/geometry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>geometry</span></a> <a href="https://masto.ai/tags/datageometry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>datageometry</span></a> <a href="https://masto.ai/tags/discretegeometry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>discretegeometry</span></a> <a href="https://masto.ai/tags/materialscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>materialscience</span></a> <br><a href="https://masto.ai/tags/hyperbolicneuralnetwork" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>hyperbolicneuralnetwork</span></a><br><a href="https://masto.ai/tags/GraphNeuralNetwork" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GraphNeuralNetwork</span></a> <a href="https://masto.ai/tags/GNNs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GNNs</span></a><br><a href="https://masto.ai/tags/topology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>topology</span></a> <a href="https://masto.ai/tags/TDA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TDA</span></a> <a href="https://masto.ai/tags/metricspaces" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>metricspaces</span></a><br><a href="https://masto.ai/tags/equivariantneuralnetwork" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>equivariantneuralnetwork</span></a> <a href="https://masto.ai/tags/enns" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>enns</span></a> <a href="https://masto.ai/tags/convolutionalneuralnetwork" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>convolutionalneuralnetwork</span></a> <a href="https://masto.ai/tags/networkscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>networkscience</span></a> <br><a href="https://masto.ai/tags/computationalchemistry" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computationalchemistry</span></a> <a href="https://masto.ai/tags/dft" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dft</span></a> <a href="https://masto.ai/tags/pinns" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pinns</span></a><br><a href="https://masto.ai/tags/optimaltransport" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>optimaltransport</span></a> <br><a href="https://masto.ai/tags/learningTheory" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>learningTheory</span></a> <a href="https://masto.ai/tags/generalization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>generalization</span></a> <br><a href="https://masto.ai/tags/expressivity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>expressivity</span></a> <br><a href="https://masto.ai/tags/marinescience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>marinescience</span></a> <a href="https://masto.ai/tags/biodiversity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>biodiversity</span></a> <a href="https://masto.ai/tags/oceanscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>oceanscience</span></a> <br><a href="https://masto.ai/tags/phylogenetics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>phylogenetics</span></a></p>
TrendingLive 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