home.social

#snn — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #snn, aggregated by home.social.

fetched live
  1. Self-generated #extracellular fields in #SNN can decorrelate #PopulationActivity, expand #dimensionality, and improve decoding. The same field imposed from outside instead synchronizes the network and impairs coding.

    Endogenous fields may not just be by-products of #NeuralActivity, but active organizers of population dynamics.

    📄 doi.org/10.64898/2026.07.28.74

    #Neuroscience #CompNeuro #PopulationCoding

  2. Two historical lineages emerged from attempts to model the neuron.

    The McCulloch-Pitts/Perceptron path emphasized logic, learning, and static representations, ultimately leading to modern deep learning.

    The Lapicque/LIF path preserved temporal dynamics, threshold-triggered events, and biophysical intuition, forming the foundation of spiking neural networks.

    The figure summarizes how these two traditions evolved, what they gained, and what they sacrificed.

    #NeuromorphicComputing #SNN #AI

  3. Aviation weather for Shannon airport (Ireland) is “METAR EINN 231030Z 21008KT 160V250 9999 SCT032 BKN120 16/09 Q1026 NOSIG” : See what it means on bigorre.org/aero/meteo/einn/en #shannonairport #airport #shannon #ireland #einn #snn #metar #aviation #aviationweather #avgeek vl

  4. Ok. I think the last widget I'll be building for my Bio-Inspired #AI and Optimization course this semester.

    Spiking Neural Network ( #SNN ) explorer

    LIF Neuron model, Rate coding, STDP, Survey of HW&SW implementations, #Neuromorphic applications & learning
    tpavlic.github.io/asu-bioinspi

  5. Just came across an elegant new #SNN framework called #nervos by Maskeen and Lashkare, which implements a two layer SNN w/ local #STDP #learning to classify, e.g., #MNIST digits. Here is an example, where I apply it to a 6-class subset of MNIST. The model reaches around 85% accuracy & the learned synapses show digit-like patterns. Quite impressive in my view, given the simplicity of the architecture & the local learning rule:

    🌍fabriziomusacchio.com/blog/202

    #CompNeuro #Neuroscience #NeuralPlasticity

  6. Spike-timing-dependent #plasticity (#STDP) is a core rule in #ComputationalNeuroscience that adjusts #synaptic strength based on precise pre- vs. postsynaptic #spike timing, enabling #TemporalCoding and #learning in #SNN. In this post, I summarize its mathematical formulation, functional consequences for learning and #memory along with a simple #Python example:

    🌍 fabriziomusacchio.com/blog/202

    #CompNeuro #Neuroscience #SNN #NeuralDynamics #NeuralPlasticity

  7. Incorporating structural #plasticity in #SpikingNeuralNetworks (#SNN) enables dynamic #synaptic connectivity, reflecting the #brain's adaptability. By modeling synaptic growth and pruning based on #calcium concentration, we can simulate processes such as #learning and #MemoryFormation. In this post, I reproduce the #NESTSimulator tutorial on structural plasticity, demonstrating its impact on network stability and #homeostasis:

    🌍 fabriziomusacchio.com/blog/202

    #CompNeuro #Neuroscience #NeuralNetworks

  8. Boeren in de provincie Groningen kunnen vanaf 16 januari subsidie aanvragen voor investeringen in duurzame landbouw. Het gaat om steun voor machines en installaties die (jonge) bedrijven toekomstbestendig maken.

    #Landbouwtransitie #verduurzaming #SNN
    rtvzulthe.nl/westerkwartier/pr

  9. Aviation weather for Shannon airport (Ireland) is “EINN 051030Z 14024G35KT 9999 -RA SCT012 BKN015 10/08 Q0982 TEMPO 4000 BKN012” : See what it means on bigorre.org/aero/meteo/einn/en #shannonairport #airport #shannon #ireland #einn #snn #metar #aviation #aviationweather #avgeek vl

  10. Lees tip -> FIOD pakt subsidiefraude aardbevingsschade aan | FIOD houdt vijf mannen aan wegens vermoedelijke subsidiefraude met aardbevingsschade in Groningen en roept andere fraudeurs op zich vrijwillig te melden bij het Openbaar Ministerie. | #aardbevingsschade #Fiod #Groningen #IMG #OpenbaarMinisterie #SNN #subsidiefraude #vastgoedondernemers #verduurzamingssubsidie |

    hbpmedia.nl/subsidiefraude-aar

  11. #Spiking #neural #networks (#SNN) running on continuous-time, noisy, and highly variable computing substrates can learn reliably with #ReinforcementLearning ... Not only in real brains, but also in mixed-signal #neuromorphic hardware! 😇

    Neuromorphic dreaming as a pathway to efficient learning in artificial agents

    doi.org/10.1088/2634-4386/ae0a

  12. Curious how #OdorDiscrimination can emerge in a biologically plausible recurrent spiking model/ #SNN? Using e-prop learning, we show heterogeneous #NeuronTuning and population trajectories in #NeuralStateSpace. Come check out my poster (#35) at 👉 #BernsteinConference, today in session I!