Netherlands eScience Center<p>🚀 We've released a new version of DIANNA, our open-source <a href="https://akademienl.social/tags/ExplainableAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ExplainableAI</span></a> (<a href="https://akademienl.social/tags/XAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>XAI</span></a>) tool designed to help researchers get insights into predictions of <a href="https://akademienl.social/tags/DeepNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepNeuralNetworks</span></a>. </p><p>What's new:<br>👉improved dashboard<br>👉extensive documentation <br>👉added tutorials</p><p>MORE: <a href="https://www.esciencecenter.nl/news/new-release-of-escience-centers-explainable-ai-tool-dianna/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">esciencecenter.nl/news/new-rel</span><span class="invisible">ease-of-escience-centers-explainable-ai-tool-dianna/</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:
533active users
101010.pl: About · Status · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.0-alpha.4
#deepneuralnetworks
0 posts · 0 participants · 0 posts today
Mattia Rigotti<p>📣 Check out our new paper "DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications", oral at <span class="h-card" translate="no"><a href="https://sigmoid.social/@aclmeeting" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>aclmeeting</span></a></span> by lead author Adam Ivankay this Wednesday!</p><p>We show adversarial attacks to <a href="https://mastodon.social/tags/explainability" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>explainability</span></a> methods for <a href="https://mastodon.social/tags/DeepNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepNeuralNetworks</span></a> in technical text domains, propose a quantification of this problem, and initial solutions.</p><p>📊 Presentation: <a href="https://virtual2023.aclweb.org/paper_P1265.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">virtual2023.aclweb.org/paper_P</span><span class="invisible">1265.html</span></a><br>📄 Paper: <a href="https://arxiv.org/abs/2307.02094" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2307.02094</span><span class="invisible"></span></a><br>💻 Code: <a href="https://github.com/ibm/domain-adaptive-attribution-robustness" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/ibm/domain-adaptive</span><span class="invisible">-attribution-robustness</span></a></p><p><a href="https://mastodon.social/tags/ACL2023" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2023</span></a> <a href="https://mastodon.social/tags/ACL2023NLP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2023NLP</span></a> <a href="https://mastodon.social/tags/NLP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLP</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/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a></p>
Nick Byrd, Ph.D.<p>Why <a href="https://nerdculture.de/tags/DeepNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepNeuralNetworks</span></a> need <a href="https://nerdculture.de/tags/Logic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Logic</span></a>:</p><p>Nick Shea (<a href="https://nerdculture.de/tags/UCL" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UCL</span></a>/#Oxford) suggests</p><p>(1) Generating novel stuff (e.g., <a href="https://nerdculture.de/tags/Dalle" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Dalle</span></a>'s art, <a href="https://nerdculture.de/tags/GPT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GPT</span></a>'s writing) is cool, but slow and inconsistent.</p><p>(2) Just a handful of logical inferences can be used *across* loads of situations (e.g., <a href="https://nerdculture.de/tags/modusPonens" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>modusPonens</span></a> works the same way every time).</p><p>So (3) by <a href="https://nerdculture.de/tags/learning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>learning</span></a> Logic, <a href="https://nerdculture.de/tags/DNNs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DNNs</span></a> would be able to recycle a few logical moves on a MASSIVE number of problems (rather than generate a novel solution from scratch for each one).</p><p><a href="https://nerdculture.de/tags/CompSci" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CompSci</span></a> <a href="https://nerdculture.de/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a></p>
Icelandic Vision Lab<p>Wow. In 24 hours, we have gone from zero to 4.4K followers, that‘s crazy. Thank you for a warm welcome and excellent tips. I gave up on replying to all of you after someone pointed out that I was spamming thousands of people – sorry! Also, please do not read too much into it if we do not respond or take a long time responding, we are a busy bunch and may simply sometimes miss your post or messages. Mastodon allows long posts so I am taking advantage of that, so here are a few things that you may – or may not – want to know.</p><p>—Who are we?—</p><p>Research in the Icelandic Vision Lab (<a href="https://visionlab.is" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">visionlab.is</span><span class="invisible"></span></a>) focuses on all things visual, with a major emphasis on higher-level or “cognitive” aspects of visual perception. It is co-run by five Principal Investigators: Árni Gunnar Ásgeirsson, Sabrina Hansmann-Roth, Árni Kristjánsson, Inga María Ólafsdóttir, and Heida Maria Sigurdardottir. Here on Mastodon, you will most likely be interacting with me – Heida – but other PIs and potentially other lab members (<a href="https://visionlab.is/people" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">visionlab.is/people</span><span class="invisible"></span></a>) may occasionally also post here as this is a joint account. If our posts are stupid and/or annoying, I will however almost surely be responsible!</p><p>—What do we do?—</p><p>Current and/or past research at IVL has looked at several visual processes, including <a href="https://neuromatch.social/tags/VisualAttention" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VisualAttention</span></a> , <a href="https://neuromatch.social/tags/EyeMovements" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EyeMovements</span></a> , <a href="https://neuromatch.social/tags/ObjectPerception" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ObjectPerception</span></a> , <a href="https://neuromatch.social/tags/FacePerception" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FacePerception</span></a> , <a href="https://neuromatch.social/tags/VisualMemory" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VisualMemory</span></a> , <a href="https://neuromatch.social/tags/VisualStatistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VisualStatistics</span></a> , and the role of <a href="https://neuromatch.social/tags/Experience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Experience</span></a> / <a href="https://neuromatch.social/tags/Learning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Learning</span></a> effects in <a href="https://neuromatch.social/tags/VisualPerception" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VisualPerception</span></a> . Some of our work concerns the basic properties of the workings of the typical adult <a href="https://neuromatch.social/tags/VisualSystem" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VisualSystem</span></a> . We have also studied the perceptual capabilities of several unique populations, including children, synesthetes, professional athletes, people with anxiety disorders, blind people, and dyslexic readers. We focus on <a href="https://neuromatch.social/tags/BehavioralMethods" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BehavioralMethods</span></a> but also make use of other techniques including <a href="https://neuromatch.social/tags/Electrophysiology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Electrophysiology</span></a> , <a href="https://neuromatch.social/tags/EyeTracking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EyeTracking</span></a> , and <a href="https://neuromatch.social/tags/DeepNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepNeuralNetworks</span></a></p><p>—Why are we here?—</p><p>We are mostly here to interact with other researchers in our field, including graduate students, postdoctoral researchers, and principal investigators. This means that our activity on Mastodon may sometimes be quite niche. This can include boosting posts from others on research papers, conferences, or work opportunities in specialized fields, partaking in discussions on debates in our field, data analysis, or the scientific review process. Science communication and outreach are hugely important, but this account is not about that as such. So we take no offence if that means that you will unfollow us, that is perfectly alright :)</p><p>—But will there still sometimes be stupid memes as promised?—</p><p>Yes. They may or may not be funny, but they will be stupid.</p><p><a href="https://neuromatch.social/tags/VisionScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VisionScience</span></a> <a href="https://neuromatch.social/tags/CognitivePsychology" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CognitivePsychology</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/StupidMemes" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>StupidMemes</span></a></p>
Paul Marrow 🇪🇺<p>I got interested in <a href="https://ecoevo.social/tags/BiologicallyInspiredComputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BiologicallyInspiredComputing</span></a> when I learned about <a href="https://ecoevo.social/tags/ArtificialLife" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialLife</span></a> <a href="https://ecoevo.social/tags/ALife" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ALife</span></a>. At that time the computing resources available were limited compared to today. Now we have <a href="https://ecoevo.social/tags/DeepNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepNeuralNetworks</span></a> <a href="https://ecoevo.social/tags/DNN" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DNN</span></a> but it is widely agreed (including by me) that they do not replace natural <a href="https://ecoevo.social/tags/cognition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cognition</span></a>. <a href="https://ecoevo.social/tags/BiologicallyInspiredComputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BiologicallyInspiredComputing</span></a> can be used as an application technology, but how do we use <a href="https://ecoevo.social/tags/Computing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Computing</span></a> to understand <a href="https://ecoevo.social/tags/Cognition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Cognition</span></a>?</p>
IT News<p>DeepMind’s new AI tool helps resolve debate over ancient Athenian decrees - Enlarge / This fragmented inscription records a decree concerning the A... - <a href="https://arstechnica.com/?p=1839561" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="">arstechnica.com/?p=1839561</span><span class="invisible"></span></a> <a href="https://schleuss.online/tags/artificialintellignece" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>artificialintellignece</span></a> <a href="https://schleuss.online/tags/deepneuralnetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>deepneuralnetworks</span></a> <a href="https://schleuss.online/tags/digitalhumanities" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>digitalhumanities</span></a> <a href="https://schleuss.online/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> <a href="https://schleuss.online/tags/gaming" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gaming</span></a>&culture <a href="https://schleuss.online/tags/ancientgreece" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ancientgreece</span></a> <a href="https://schleuss.online/tags/ancienttexts" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ancienttexts</span></a> <a href="https://schleuss.online/tags/science" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>science</span></a></p>
IT News<p>Deep Learning Enables Intuitive Prosthetic Control - Prosthetic limbs have been slow to evolve from simple motionless replicas of human... - <a href="https://hackaday.com/2021/05/27/deep-learning-enables-intuitive-prosthetic-control/" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2021/05/27/deep-l</span><span class="invisible">earning-enables-intuitive-prosthetic-control/</span></a> <a href="https://schleuss.online/tags/deepneuralnetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>deepneuralnetworks</span></a> <a href="https://schleuss.online/tags/machinelearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinelearning</span></a> <a href="https://schleuss.online/tags/neuralnetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuralnetworks</span></a> <a href="https://schleuss.online/tags/prostheticarm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>prostheticarm</span></a> <a href="https://schleuss.online/tags/prosthetic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>prosthetic</span></a> <a href="https://schleuss.online/tags/cuda" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cuda</span></a> <a href="https://schleuss.online/tags/arm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>arm</span></a></p>
OSTechNix<p>A collection of exciting video lectures to learn deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP.</p><p><a href="https://github.com/kmario23/deep-learning-drizzle" rel="nofollow noopener" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/kmario23/deep-learn</span><span class="invisible">ing-drizzle</span></a></p><p><a href="https://floss.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://floss.social/tags/DeepLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepLearning</span></a> <a href="https://floss.social/tags/deepneuralnetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>deepneuralnetworks</span></a> <a href="https://floss.social/tags/computervision" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computervision</span></a> <a href="https://floss.social/tags/nlp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlp</span></a> <a href="https://floss.social/tags/reinforcementlearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>reinforcementlearning</span></a> <a href="https://floss.social/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</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