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:
πhttps://www.fabriziomusacchio.com/blog/2026-02-16-nervos_stdp_snn_simulation_on_mnist/
