Dan Goodman<p>We are hiring a postdoc. It's a broadly scoped position but I think it would be of interest to someone in <a href="https://neuromatch.social/tags/Neuromorphic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neuromorphic</span></a> or <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a>. See ad below. Inquiries to Dan Akarca because I will be on holiday.</p><p>Note, the application deadline is very soon! (Unavoidable admin issues.)</p><p><a href="https://www.imperial.ac.uk/jobs/search-jobs/description/index.php?jobId=24879&jobTitle=Research+Associate*+in+NeuroAI%2C+Neuromorphic+Systems%2C+Hardware-Software+Co-Design" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">imperial.ac.uk/jobs/search-job</span><span class="invisible">s/description/index.php?jobId=24879&jobTitle=Research+Associate*+in+NeuroAI%2C+Neuromorphic+Systems%2C+Hardware-Software+Co-Design</span></a></p>
mastodon.ie is one of the many independent Mastodon servers you can use to participate in the fediverse.
Irish Mastodon - run from Ireland, we welcome all who respect the community rules and members.
Administered by:
Server stats:
1.6Kactive users
mastodon.ie: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.2
#spikingneuralnetworks
0 posts · 0 participants · 0 posts today
Aaron<p><span class="h-card" translate="no"><a href="https://yt.lostpod.space/accounts/root" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>root</span></a></span> The closest technologies we have to how the human brain works are not LLMs, but some less well-known ones: reinforcement learning algorithms and hyperdimensional computing. If you want to see what HDC is capable of, check out this video:</p><p><a href="https://youtu.be/P_WRCyNQ9KY?si=JgAuOJQmsQ6tVIiO" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/P_WRCyNQ9KY?si=JgAuOJ</span><span class="invisible">QmsQ6tVIiO</span></a></p><p><a href="https://techhub.social/tags/HDC" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HDC</span></a> <a href="https://techhub.social/tags/HyperdimensionalComputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HyperdimensionalComputing</span></a><br><a href="https://techhub.social/tags/VSA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VSA</span></a> <a href="https://techhub.social/tags/VectorSymbolicArchitecture" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VectorSymbolicArchitecture</span></a><br><a href="https://techhub.social/tags/HRR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HRR</span></a> <a href="https://techhub.social/tags/HolographicReducedRepresentation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HolographicReducedRepresentation</span></a><br><a href="https://techhub.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a><br><a href="https://techhub.social/tags/AGI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AGI</span></a> <a href="https://techhub.social/tags/ArtificialGeneralIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialGeneralIntelligence</span></a><br><a href="https://techhub.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a></p>
Pyrzout :vm:<p>Spiking Neural Networks: Brain-Inspired Chips That Could Keep Your Data Safe <a href="https://www.securityweek.com/spiking-neural-networks-brain-inspired-chips-that-could-keep-your-data-safe/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">securityweek.com/spiking-neura</span><span class="invisible">l-networks-brain-inspired-chips-that-could-keep-your-data-safe/</span></a> <a href="https://social.skynetcloud.site/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://social.skynetcloud.site/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> <a href="https://social.skynetcloud.site/tags/dataprotection" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dataprotection</span></a> <a href="https://social.skynetcloud.site/tags/privacy" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>privacy</span></a></p>
Pyrzout :vm:<p>Spiking Neural Networks: Brain-Inspired Chips That Could Keep Your Data Safe <a href="https://www.securityweek.com/spiking-neural-networks-brain-inspired-chips-that-could-keep-your-data-safe/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">securityweek.com/spiking-neura</span><span class="invisible">l-networks-brain-inspired-chips-that-could-keep-your-data-safe/</span></a> <a href="https://social.skynetcloud.site/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://social.skynetcloud.site/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> <a href="https://social.skynetcloud.site/tags/dataprotection" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>dataprotection</span></a> <a href="https://social.skynetcloud.site/tags/privacy" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>privacy</span></a></p>
Dan Goodman<p>Word cloud of abstracts we've received for <a href="https://neuromatch.social/tags/SNUFA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SNUFA</span></a> <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> conference 2024. Register (free) by tomorrow afternoon UTC if you want to take part in selecting which abstracts get offered talk slots at the workshop!</p><p><a href="https://snufa.net/2024/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">snufa.net/2024/</span><span class="invisible"></span></a></p><p><a href="https://neuromatch.social/tags/neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuroscience</span></a></p>
Dan Goodman<p>We got 50% more submissions this year for the <a href="https://neuromatch.social/tags/SNUFA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SNUFA</span></a> <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> conference compared to last year: thanks! ❤️</p><p>We will shortly send out to registered participants a survey to allow you to take part in the approval voting scheme that will decide which abstracts we select as talks.</p><p>Register soon if you want to take part!</p><p><a href="https://snufa.net/2024/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">snufa.net/2024/</span><span class="invisible"></span></a></p>
Dan Goodman<p>Submit your abstracts for the <a href="https://neuromatch.social/tags/SNUFA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SNUFA</span></a> <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> conference by tomorrow The conference is free, online and usually has around 700 highly engaged participants. Talks are selected by participant interest.</p><p>Please do signal boost this!</p><p><a href="https://snufa.net/2024/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">snufa.net/2024/</span><span class="invisible"></span></a></p><p><a href="https://neuromatch.social/tags/compneuro" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>compneuro</span></a> <a href="https://neuromatch.social/tags/neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuroscience</span></a></p>
Laurent Perrinet<ul><li>Extends the HOTS algorithm to increase its performance by adding a homeostatic gain control on the activity of neurons to improve the learning of spatio-temporal patterns, we prove an analogy with off-the-shelf LIF <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> </li></ul><p>This needs a hand clap ! 👏</p>
Dan Goodman<p>New preprint on our "collaborative modelling of the brain" (COMOB) project. Over the last two years, a group of us (led by <span class="h-card" translate="no"><a href="https://neuromatch.social/@marcusghosh" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>marcusghosh</span></a></span>) have been working together, openly, online, with anyone free to join, on a computational neuroscience research project</p><p><a href="https://www.biorxiv.org/content/10.1101/2024.07.19.604252v1" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">biorxiv.org/content/10.1101/20</span><span class="invisible">24.07.19.604252v1</span></a></p><p>This was an experiment in a more bottom up, collaborative way of doing science, rather than the hierarchical PI-led model. So how did we do it?</p><p>We started from the tutorial I gave at <span class="h-card" translate="no"><a href="https://neuromatch.social/@CosyneMeeting" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>CosyneMeeting</span></a></span> 2022 on spiking neural networks that included a starter Jupyter notebook that let you train a spiking neural network model on a sound localisation task.</p><p><a href="https://neural-reckoning.github.io/cosyne-tutorial-2022/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">neural-reckoning.github.io/cos</span><span class="invisible">yne-tutorial-2022/</span></a></p><p><a href="https://www.youtube.com/watch?v=GTXTQ_sOxak&list=PL09WqqDbQWHGJd7Il3yVxiBts5nRSxvJ4&index=1" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">youtube.com/watch?v=GTXTQ_sOxa</span><span class="invisible">k&list=PL09WqqDbQWHGJd7Il3yVxiBts5nRSxvJ4&index=1</span></a></p><p>Participants were free to use and adapt this to any question they were interested in (we gave some ideas for starting points, but there was no constraint). Participants worked in groups or individually, sharing their work on our repository and joining us for monthly meetings. </p><p>The repository was set up to automatically build a website using <span class="h-card" translate="no"><a href="https://fosstodon.org/@mystmarkdown" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>mystmarkdown</span></a></span> showing the current work in progress of all projects, and (later in the project) the paper as we wrote it. This kept everyone up to date with what was going on.</p><p><a href="https://comob-project.github.io/snn-sound-localization/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">comob-project.github.io/snn-so</span><span class="invisible">und-localization/</span></a></p><p>We started from a simple feedforward network of leaky integrate-and-fire neurons, but others adapted it to include learnable delays, alternative neuron models, biophysically detailed models, incorporated Dale's law, etc.</p><p>We found some interesting results, including that shorter time constants improved performance (consistent with what we see in the auditory system). Surprisingly, the network seemed to be using an "equalisation cancellation" strategy rather than the expected coincidence detection.</p><p>Ultimately, our scientific results were not incredibly strong, but we think this was a valuable experiment for a number of reasons. Firstly, it shows that there are other ways of doing science. Secondly, many people got to engage in a research experience they otherwise wouldn't. Several participants have been motivated to continue their work beyond this project. It also proved useful for generating teaching material, and a number of MSc projects were based on it.</p><p>With that said, we learned some lessons about how to do this better, and yes, we will be doing this again (call for participation in September/October hopefully). The main challenge will be to keep the project more focussed without making it top down / hierarchical.</p><p>We believe this is possible, and we are inspired by the recent success of the Busy Beaver challenge, a bottom up project of mathematics amateurs that found a proof to a 40 year old conjecture.</p><p><a href="https://www.quantamagazine.org/amateur-mathematicians-find-fifth-busy-beaver-turing-machine-20240702/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">quantamagazine.org/amateur-mat</span><span class="invisible">hematicians-find-fifth-busy-beaver-turing-machine-20240702/</span></a></p><p>We will be calling for proposals for the next project, engaging in an open discussion with all participants to refine the ideas before starting, and then inviting the proposer of the most popular project to act as a 'project lead' keeping it focussed without being hierarchical.</p><p>If you're interested in being involved in that, please join our (currently fairly quiet) new discord server, or follow me or <span class="h-card" translate="no"><a href="https://neuromatch.social/@marcusghosh" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>marcusghosh</span></a></span> for announcements.</p><p><a href="https://discord.gg/kUzh5MHjVE" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">discord.gg/kUzh5MHjVE</span><span class="invisible"></span></a></p><p>I'm excited for a future where scientists work more collaboratively, and where everyone can participate. Diversity will lead to exciting new ideas and progress. Computational science has huge potential here, something we're also pursuing at <span class="h-card" translate="no"><a href="https://neuromatch.social/@neuromatch" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>neuromatch</span></a></span>.</p><p>Let's make it happen!</p><p><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/computationalscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computationalscience</span></a> <a href="https://neuromatch.social/tags/computationalneuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computationalneuroscience</span></a> <a href="https://neuromatch.social/tags/compneuro" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>compneuro</span></a> <a href="https://neuromatch.social/tags/science" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>science</span></a> <a href="https://neuromatch.social/tags/metascience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>metascience</span></a> <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> <a href="https://neuromatch.social/tags/auditory" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>auditory</span></a></p>
Dan Goodman<p>Could we decide if a simulated spiking neural network uses spike timing or not? Given that we have full access to the state of the network and can simulate perturbations. Ideas for how we could decide? Would everyone agree? <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/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> <a href="https://neuromatch.social/tags/computationalneuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computationalneuroscience</span></a> <a href="https://neuromatch.social/tags/compneuro" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>compneuro</span></a></p>
Fabrizio Musacchio<p>In 2000, Nicolas Brunel presented a framework for studying sparsely connected <a href="https://sigmoid.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> (<a href="https://sigmoid.social/tags/SNN" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SNN</span></a>) with random connectivity & varied excitation-inhibition balance. The model, characterized by high sparseness & low firing rates, captures diverse neural dynamics such as synchronized regular and asynchronous irregular activity and global oscillations. Here is a brief summary of these concepts & a <a href="https://sigmoid.social/tags/PythonTuroial" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PythonTuroial</span></a> using the <a href="https://sigmoid.social/tags/NESTsimulator" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NESTsimulator</span></a>.</p><p>🌍 <a href="https://www.fabriziomusacchio.com/blog/2024-07-21-brunel_network/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">fabriziomusacchio.com/blog/202</span><span class="invisible">4-07-21-brunel_network/</span></a><br><a href="https://sigmoid.social/tags/CompNeuro" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CompNeuro</span></a> <a href="https://sigmoid.social/tags/Neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neuroscience</span></a></p>
Dan Goodman<p>SPIKING NEURAL NETWORKS!</p><p>If you love them, join us at SNUFA24. Free, online workshop, Nov 5-6 (2-6pm CET). Usually ~700 participants.</p><p>Invited speakers: Chiara Bartolozzi, David Kappel, Anna Levina, Christian Machens</p><p>Posters + 8 contributed talks selected by participant vote.</p><p>Abstract submission is quick and easy (300 word max), and now open until the deadline Sept 27.</p><p>Registration is free, but mandatory.</p><p>Hope to see you there!</p><p><a href="https://snufa.net/2024/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">snufa.net/2024/</span><span class="invisible"></span></a></p><p><a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</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/computationalneuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computationalneuroscience</span></a> <a href="https://neuromatch.social/tags/neuromorphic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuromorphic</span></a> <a href="https://neuromatch.social/tags/neuromorphiccomputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuromorphiccomputing</span></a> <a href="https://neuromatch.social/tags/Neuromorphicengineering" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neuromorphicengineering</span></a></p>
Fabrizio Musacchio<p>The <a href="https://sigmoid.social/tags/NEST" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NEST</span></a> <a href="https://sigmoid.social/tags/simulator" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>simulator</span></a> is a powerful software for simulating large-scale <a href="https://sigmoid.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> (<a href="https://sigmoid.social/tags/SNN" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SNN</span></a>). I’ve composed an introductory <a href="https://sigmoid.social/tags/tutorial" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tutorial</span></a> showing the main commands for getting started. It's applied to examples with single neurons to reduce complexity. Feel free to share:</p><p>🌍 <a href="https://www.fabriziomusacchio.com/blog/2024-06-16-nest_single_neuron_example/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">fabriziomusacchio.com/blog/202</span><span class="invisible">4-06-16-nest_single_neuron_example/</span></a></p><p><a href="https://sigmoid.social/tags/CompNeuro" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CompNeuro</span></a> <a href="https://sigmoid.social/tags/ComputationalNeuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputationalNeuroscience</span></a> <a href="https://sigmoid.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> <a href="https://sigmoid.social/tags/PythonTutorial" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PythonTutorial</span></a> <a href="https://sigmoid.social/tags/NESTSimulator" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NESTSimulator</span></a></p>
Fabrizio Musacchio<p>Due to its computational efficiency and biological plausibility, the <a href="https://sigmoid.social/tags/IzhikevichModel" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>IzhikevichModel</span></a> is an exceptional tool for understanding <a href="https://sigmoid.social/tags/neuronal" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuronal</span></a> interactions within <a href="https://sigmoid.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> (<a href="https://sigmoid.social/tags/SNN" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SNN</span></a>). Here’s a quick <a href="https://sigmoid.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> implementation of Izhikevich's original <a href="https://sigmoid.social/tags/Matlab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Matlab</span></a> code along with examples using different synaptic weights and neuron types, each leading to diverse spiking behaviors and network dynamics:</p><p>🌍<a href="https://www.fabriziomusacchio.com/posts/izhikevich_network_model/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">fabriziomusacchio.com/posts/iz</span><span class="invisible">hikevich_network_model/</span></a> </p><p><a href="https://sigmoid.social/tags/CompNeuro" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CompNeuro</span></a> <a href="https://sigmoid.social/tags/Neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neuroscience</span></a> <a href="https://sigmoid.social/tags/ComputationalScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputationalScience</span></a> <a href="https://sigmoid.social/tags/NeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NeuralNetworks</span></a> <a href="https://sigmoid.social/tags/modeling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>modeling</span></a></p>
Dan Goodman<p>Spiking neural network community. We are thinking of holding the annual SNUFA workshop on Nov 5-6 or 12-13. Preferences? Are there any clashes we should know about? <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</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/ComputationalNeuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputationalNeuroscience</span></a></p>
Laurent Perrinet<p>Dear colleagues,</p><p>It's a pleasure to share with you this fully-funded <a href="https://neuromatch.social/tags/PhD" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PhD</span></a> position in <a href="https://neuromatch.social/tags/computational" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>computational</span></a> neuroscience in interaction with <a href="https://neuromatch.social/tags/neuromorphic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuromorphic</span></a> engineering and <a href="https://neuromatch.social/tags/neuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuroscience</span></a>:</p><p><a href="https://laurentperrinet.github.io/post/2024-05-03_phd-position_focus-of-attention/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">laurentperrinet.github.io/post</span><span class="invisible">/2024-05-03_phd-position_focus-of-attention/</span></a></p><p>TL;DR: This PhD subject focuses on the association between <a href="https://neuromatch.social/tags/attention" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>attention</span></a> and <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> for defining new efficient AI models for embedded systems such as drones, robots and more generally autonomous systems. The thesis will take place between the LEAT research lab in Sophia-Antipolis and the INT institute in Marseille which both develop complementary approaches on bio-inspired AI from neuroscience to embedded systems design. </p><p>The application should include :<br>• Curriculum vitæ,</p><p>• Motivation Letter,</p><p>• Letter of recommendation of the master supervisor.</p><p>and sent to Benoit Miramond benoit.miramond@unice.fr, Laurent Perrinet Laurent.Perrinet@univ-amu.fr, and Laurent Rodriguez laurent.rodriguez@univ-cotedazur.fr</p><p>Cheers,<br>Laurent</p><p>PS: related references:</p><ul><li><p>Emmanuel Daucé, Pierre Albigès, Laurent U Perrinet (2020). A dual foveal-peripheral visual processing model implements efficient saccade selection. Journal of Vision. doi: <a href="https://doi.org/10.1167/jov.20.8.22" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.1167/jov.20.8.22</span><span class="invisible"></span></a></p></li><li><p>Jean-Nicolas Jérémie, Emmanuel Daucé, Laurent U Perrinet (2024). Retinotopic Mapping Enhances the Robustness of Convolutional Neural Networks. arXiv: <a href="https://arxiv.org/abs/2402.15480" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2402.15480</span><span class="invisible"></span></a></p></li></ul>
Brian simulator<p>Just in time for your weekend, we released Brian 2.6, the new version of your friendly spiking network simulator. 🚀<br>It comes with many small improvements, bug and compatibility fixes, and offers a major new feature for running standalone simulations repeatedly (or in parallel) without recompiling code. In addition, it comes with general infrastructure improvements all around (official wheels for Python 3.12! Docker images on Docker hub! Apple Silicon builds/tests!).<br>Enjoy (and let us know if you run into any issues, of course…) 🥳</p><p><a href="https://briansimulator.org/posts/2024/brian-26/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">briansimulator.org/posts/2024/</span><span class="invisible">brian-26/</span></a></p><p><a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> <a href="https://neuromatch.social/tags/ComputationalNeuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputationalNeuroscience</span></a> <a href="https://neuromatch.social/tags/FOSS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FOSS</span></a> <a href="https://neuromatch.social/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Python</span></a> <a href="https://neuromatch.social/tags/NoDeployFriday" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NoDeployFriday</span></a></p>
Laurent Perrinet<p>Special Session on <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a> and <a href="https://neuromatch.social/tags/Neuromorphic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Neuromorphic</span></a> Computing at the 33rd International Conference on Artificial Neural Networks (ICANN) 2024 - Call for Papers</p><blockquote><p>Sep 17 - 20, Lugano, Switzerland</p></blockquote><p>The special session invites contributions on recent advances in spiking neural networks. Spiking neural networks have gained substantial attention recently as a candidate for low latency and low power AI substrate, with implementations being explored in neuromorphic hardware. This special session aims to bring together practitioners interested in efficient learning algorithms, data representations, and applications.</p><p>ORGANIZERS: </p><ul><li>Sander Bohté (CWI Amsterdam, Netherlands)</li><li>Sebastian Otte (University of Lübeck, Germany)</li></ul><p>Find more details at: <a href="https://e-nns.org/wp-content/uploads/2024/ICANN2024-SNNC-CfP.pdf" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">e-nns.org/wp-content/uploads/2</span><span class="invisible">024/ICANN2024-SNNC-CfP.pdf</span></a></p><p><a href="https://neuromatch.social/tags/icann" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>icann</span></a> <a href="https://neuromatch.social/tags/enns" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>enns</span></a> <a href="https://neuromatch.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a> <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/spiking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>spiking</span></a> <a href="https://neuromatch.social/tags/snn" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>snn</span></a> <a href="https://neuromatch.social/tags/neuromorphic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>neuromorphic</span></a> <a href="https://neuromatch.social/tags/edgeai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>edgeai</span></a></p>
Dan Goodman<p>I'm on the latest episode of Brain Inspired talking about <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/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a>, <a href="https://neuromatch.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> and <a href="https://neuromatch.social/tags/Metascience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Metascience</span></a>! Thanks Paul Middlebrooks (not on Mastodon I think) for the invite and the extremely fun conversation. For the explanation of why this picture you'll have to listen to the episode. 😉</p><p><a href="https://braininspired.co/podcast/183/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">braininspired.co/podcast/183/</span><span class="invisible"></span></a></p><p>Also, if you're not yet listening to Brain Inspired you should be - and support Paul on Patreon. He provides this free for the community with no adverts. What a hero!</p>
Brian simulator<p>We are finally on Mastodon, time for a little <a href="https://neuromatch.social/tags/introduction" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>introduction</span></a> 👋 !</p><p>Brian is a <a href="https://neuromatch.social/tags/FOSS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FOSS</span></a> simulator for biological <a href="https://neuromatch.social/tags/SpikingNeuralNetworks" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpikingNeuralNetworks</span></a>, for research in <a href="https://neuromatch.social/tags/ComputationalNeuroscience" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputationalNeuroscience</span></a> and beyond. It makes it easy to go from a high-level model description in Python, based on mathematical equations and physical units, to a simulation running efficiently on the CPU or GPU.</p><p>We have a friendly community and extensive documentation, links to everything on our homepage: <a href="https://briansimulator.org" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">briansimulator.org</span><span class="invisible"></span></a></p><p>This account will mostly announce news (releases, other notable events), but we're also looking forward to discussing with y'all 💬 </p><p><a href="https://neuromatch.social/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</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/researchsoftware" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>researchsoftware</span></a> <a href="https://neuromatch.social/tags/introductions" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>introductions</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