Mastodon

Christophe BousquetHere is a nice paper on how to <a href="https://fediscience.org/tags/identify" class="mention hashtag" rel="nofollow noopener" target="_blank">#identify</a> <a href="https://fediscience.org/tags/winning" class="mention hashtag" rel="nofollow noopener" target="_blank">#winning</a> strategies using <a href="https://fediscience.org/tags/explainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainable</a> <a href="https://fediscience.org/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#MachineLearning</a> in <a href="https://fediscience.org/tags/TeamSports" class="mention hashtag" rel="nofollow noopener" target="_blank">#TeamSports</a>, with a special emphasis on <a href="https://fediscience.org/tags/rugby" class="mention hashtag" rel="nofollow noopener" target="_blank">#rugby</a>.A machine learning and explainability-driven methodology for identifying winning strategies in Rugby Union<a href="https://www.sciencedirect.com/science/article/pii/S2772662225000244" rel="nofollow noopener" translate="no" target="_blank">https://www.sciencedirect.com/science/article/pii/S2772662225000244</a>

LLMsWhy do LLMs have emergent properties? Large language models display emergence behaviors: when the... <a href="https://www.johndcook.com/blog/2025/05/08/why-do-llms-have-emergent-properties/" rel="nofollow noopener" target="_blank">https://www.johndcook.com/blog/2025/05/08/why-do-llms-have-emergent-properties/</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/AI" target="_blank">#AI</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Algorithms" target="_blank">#Algorithms</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Artificial" target="_blank">#Artificial</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Intelligence" target="_blank">#Intelligence</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Machine" target="_blank">#Machine</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/learning" target="_blank">#learning</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/explainable" target="_blank">#explainable</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/AI" target="_blank">#AI</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/large" target="_blank">#large</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/language" target="_blank">#language</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/models" target="_blank">#models</a> <a href="https://awakari.com/pub-msg.html?id=PYKVrxwtkwZOGyCvIhgteAnSiG0&interestId=LLMs" rel="nofollow noopener" target="_blank">Result Details</a>

LLMsFormulation of Feature Circuits with Sparse Autoencoders in LLM Large Language models (LLMs) have... <a href="https://towardsdatascience.com/formulation-of-feature-circuits-with-sparse-autoencoders-in-llm/" rel="nofollow noopener" target="_blank">https://towardsdatascience.com/formulation-of-feature-circuits-with-sparse-autoencoders-in-llm/</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Large" target="_blank">#Large</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Language" target="_blank">#Language</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Models" target="_blank">#Models</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Explainable" target="_blank">#Explainable</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Ai" target="_blank">#Ai</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Machine" target="_blank">#Machine</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Learning" target="_blank">#Learning</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Neural" target="_blank">#Neural</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Networks" target="_blank">#Networks</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Sparse" target="_blank">#Sparse</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Autoencoder" target="_blank">#Autoencoder</a> <a href="https://awakari.com/pub-msg.html?id=5k34zYeeVmwIurdVpqQRuOI3aOO" rel="nofollow noopener" target="_blank">Event Attributes</a>

LLMsAMD and Johns Hopkins Researchers Develop AI Agent Framework to Automate Scientific Research Proc... <a href="https://www.infoq.com/news/2025/01/amd-jhu-ai-lab-research-agent/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global" rel="nofollow noopener" target="_blank">https://www.infoq.com/news/2025/01/amd-jhu-ai-lab-research-agent/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/ChatGPT" target="_blank">#ChatGPT</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Generative" target="_blank">#Generative</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/AI" target="_blank">#AI</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Deep" target="_blank">#Deep</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Learning" target="_blank">#Learning</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/OpenAI" target="_blank">#OpenAI</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Google" target="_blank">#Google</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/DeepMind" target="_blank">#DeepMind</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Explainable" target="_blank">#Explainable</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/AI" target="_blank">#AI</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Machine" target="_blank">#Machine</a> <a href="https://awakari.com/pub-msg.html?id=5hZUnqzgLPL3cedNEqYe5h9CS6C" rel="nofollow noopener" target="_blank">Event Attributes</a>

LLMsAMD and Johns Hopkins Researchers Develop AI Agent Framework to Automate Scientific Research Proc... <a href="https://www.infoq.com/news/2025/01/amd-jhu-ai-lab-research-agent/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global" rel="nofollow noopener" target="_blank">https://www.infoq.com/news/2025/01/amd-jhu-ai-lab-research-agent/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=global</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Artificial" target="_blank">#Artificial</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Intelligence" target="_blank">#Intelligence</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/AI" target="_blank">#AI</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Architecture" target="_blank">#Architecture</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Explainable" target="_blank">#Explainable</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/AI" target="_blank">#AI</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Machine" target="_blank">#Machine</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/Learning" target="_blank">#Learning</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/OpenAI" target="_blank">#OpenAI</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/ChatGPT" target="_blank">#ChatGPT</a> <a rel="nofollow noopener" class="mention hashtag" href="https://mastodon.social/tags/AIOps" target="_blank">#AIOps</a> <a href="https://awakari.com/pub-msg.html?id=JcsqXrVoBuFmjSPjDYwcLxKjbJQ" rel="nofollow noopener" target="_blank">Event Attributes</a>

Muse™ - Listen to your MuseExplainable AI: Thinking Like a Machine | by Joseph George Lewis | Towards AI<a href="https://pub.towardsai.net/explainable-ai-thinking-like-a-machine-e40fc77949ac" target="_blank" rel="nofollow noopener" translate="no">https://pub.towardsai.net/explainable-ai-thinking-like-a-machine-e40fc77949ac</a><a href="https://mastodon.world/tags/ExplainableAI" class="mention hashtag" rel="tag">#ExplainableAI</a> <a href="https://mastodon.world/tags/ethics" class="mention hashtag" rel="tag">#ethics</a> <a href="https://mastodon.world/tags/ethicalai" class="mention hashtag" rel="tag">#ethicalai</a> <a href="https://mastodon.world/tags/Machine" class="mention hashtag" rel="tag">#Machine</a> <a href="https://mastodon.world/tags/Interpretable" class="mention hashtag" rel="tag">#Interpretable</a> <a href="https://mastodon.world/tags/Explainable" class="mention hashtag" rel="tag">#Explainable</a> <a href="https://mastodon.world/tags/XAI" class="mention hashtag" rel="tag">#XAI</a> <a href="https://mastodon.world/tags/technology" class="mention hashtag" rel="tag">#technology</a>

Gnôsis - Alexandre MARTINExplainable AI: Thinking Like a Machine | by Joseph George Lewis | Towards AI<a href="https://pub.towardsai.net/explainable-ai-thinking-like-a-machine-e40fc77949ac" rel="nofollow noopener" translate="no" target="_blank">https://pub.towardsai.net/explainable-ai-thinking-like-a-machine-e40fc77949ac</a><a href="https://mastodon.social/tags/ExplainableAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#ExplainableAI</a> <a href="https://mastodon.social/tags/ethics" class="mention hashtag" rel="nofollow noopener" target="_blank">#ethics</a> <a href="https://mastodon.social/tags/ethicalai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ethicalai</a> <a href="https://mastodon.social/tags/Machine" class="mention hashtag" rel="nofollow noopener" target="_blank">#Machine</a> <a href="https://mastodon.social/tags/Interpretable" class="mention hashtag" rel="nofollow noopener" target="_blank">#Interpretable</a> <a href="https://mastodon.social/tags/Explainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#Explainable</a> <a href="https://mastodon.social/tags/XAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#XAI</a> <a href="https://mastodon.social/tags/technology" class="mention hashtag" rel="nofollow noopener" target="_blank">#technology</a>

Computer Vision Group JenaWhen using <a href="https://fediscience.org/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#machinelearning</a> for tasks in <a href="https://fediscience.org/tags/geosciences" class="mention hashtag" rel="nofollow noopener" target="_blank">#geosciences</a>, you should aim for <a href="https://fediscience.org/tags/interpretability" class="mention hashtag" rel="nofollow noopener" target="_blank">#interpretability</a>! Why this is the case and how to go about it is the topic of a brand-new article in the open access journal "Earth's Future" by Shijie Jiang and an interdisciplinary group of colleagues. Check it out!<a href="https://doi.org/10.1029/2024EF004540" rel="nofollow noopener" translate="no" target="_blank">https://doi.org/10.1029/2024EF004540</a><a href="https://fediscience.org/tags/Explainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#Explainable</a> <a href="https://fediscience.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://fediscience.org/tags/XAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#XAI</a>

Anita Graser 🇪🇺🇺🇦🇬🇪Happy to announce our latest <a href="https://fosstodon.org/tags/preprint" class="mention hashtag" rel="nofollow noopener" target="_blank">#preprint</a> short paper 📝: "Towards <a href="https://fosstodon.org/tags/eXplainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#eXplainable</a> <a href="https://fosstodon.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> for <a href="https://fosstodon.org/tags/MobilityDataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#MobilityDataScience</a>" <a href="https://arxiv.org/abs/2307.08461" rel="nofollow noopener" target="_blank">https://arxiv.org/abs/2307.08461</a>I'd love to hear your thoughts and experiences with <a href="https://fosstodon.org/tags/XAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#XAI</a> in <a href="https://fosstodon.org/tags/SpatialDataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#SpatialDataScience</a> <a href="https://fosstodon.org/tags/GISchat" class="mention hashtag" rel="nofollow noopener" target="_blank">#GISchat</a>

time belongs wasted<a href="https://mastodon.online/@AmiW" class="u-url mention" rel="nofollow noopener" target="_blank">@AmiW</a> Although the message is clear, I think that it would not have needed such a "<a href="https://mastodon.art/tags/provocation" class="mention hashtag" rel="nofollow noopener" target="_blank">#provocation</a>" / somehow different, "compatible", could have been implemented satisfactorily. Photography should also as art still remain (technically) "<a href="https://mastodon.art/tags/explainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainable</a>". Especially in times where we are already overchallenged with clumsy falsifications by <a href="https://mastodon.art/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a>. I find myself abused in my sensations, at least "used", when I see something different than I expect.

LupposofiKuka kontrolloi ketä? -kysytään eilen ilmestyneessä EaIT-jounaalin artikkelissa liittyen tekoälyyn turvallisuusalalla, <a href="https://link.springer.com/article/10.1007/s10676-023-09686-x" rel="nofollow noopener" target="_blank">https://link.springer.com/article/10.1007/s10676-023-09686-x</a>. Tämä toisena esimerkkinä kehumastani tuoreudesta ja ajankohtaisuudesta SEP-entryn OIR-linkeissä. "Merkittävän inhimillisen kontrollin" pohdinnat yleistynevät laajemminkin, vaikka esimerkkinä oli vain pommidroonin AI-avusteinen pudottaminen.Asioita tutkitaan siksi, että ei kuvitella vielä tiedettävän.<a href="https://mastodontti.fi/tags/teko%C3%A4ly" class="mention hashtag" rel="nofollow noopener" target="_blank">#tekoäly</a> <a href="https://mastodontti.fi/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://mastodontti.fi/tags/security" class="mention hashtag" rel="nofollow noopener" target="_blank">#security</a> <a href="https://mastodontti.fi/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#research</a> <a href="https://mastodontti.fi/tags/explainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainable</a>

Benoît Allard<a href="https://osna.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> doesn't have to be a black-box. There is a real need to make it <a href="https://osna.social/tags/explainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainable</a>. I can only see this getting bigger as the time comes. <a href="https://osna.social/tags/INNOQ" class="mention hashtag" rel="nofollow noopener" target="_blank">#INNOQ</a>. Article in german.<a href="https://www.innoq.com/de/articles/2022/12/ki-systeme-mlops-model-governance-explainable-ai/" rel="nofollow noopener" target="_blank">https://www.innoq.com/de/articles/2022/12/ki-systeme-mlops-model-governance-explainable-ai/</a>

Dennis Alexis Valin Dittrich<a href="https://fediscience.org/tags/Fair" class="mention hashtag" rel="nofollow noopener" target="_blank">#Fair</a> and <a href="https://fediscience.org/tags/Explainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#Explainable</a> <a href="https://fediscience.org/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#MachineLearning</a> <a href="https://opendatascience.com/fair-and-explainable-machine-learning/" rel="nofollow noopener" target="_blank">https://opendatascience.com/fair-and-explainable-machine-learning/</a> <a href="https://fediscience.org/tags/Bias" class="mention hashtag" rel="nofollow noopener" target="_blank">#Bias</a>

Bruno Hebling VieiraVery cool paper on ML interpretability and explainability. I was surprised I hadn't come across it before <a href="https://arxiv.org/abs/2012.01805" rel="nofollow noopener" target="_blank">https://arxiv.org/abs/2012.01805</a><a href="https://mastodon.online/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#machinelearning</a> <a href="https://mastodon.online/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#ai</a> <a href="https://mastodon.online/tags/explainable" class="mention hashtag" rel="nofollow noopener" target="_blank">#explainable</a> <a href="https://mastodon.online/tags/eth" class="mention hashtag" rel="nofollow noopener" target="_blank">#eth</a>

Jordan Maris 🇪🇺 🇺🇦 #NAFOMYTH #4: IT DOESN'T MATTER THAT <a href="https://eupolicy.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> IS NOT <a href="https://eupolicy.social/tags/EXPLAINABLE" class="mention hashtag" rel="nofollow noopener" target="_blank">#EXPLAINABLE</a>, BECAUSE HUMANS DON'T ALWAYS EXPLAIN THEIR DECISIONS EITHER.False: If a citizen wants to contest a decision, then the person making that decision must explain it. Most AI based on machine learning is not explainable(1/2)..

Recent searches

Search options

Administered by:

Server stats:

#EXPLAINABLE