Reproduce “Upper bounds on the number of causal pieces in spiking neural networks” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Dominik Dold, Dennis Elbrächter, Philipp Petersen
The authors count causal pieces in single-spike networks by considering timing-compatible subnetworks, since spike-time ordering excludes some connection patterns. Their combinatorial bound assumes neurons in each layer receive the same presynaptic spike times. For nLIF neurons with Dirac-delta synapses, the upper bound is R(N0), the number of weak orders of input times, independent of depth and width.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.