Reproduce “Controlling the latency in temporal coded spiking models for neuromorphic datasets” 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
Alban Gattepaille, Alexandre Muzy
The authors extend a Delay Neural Network (DeNN) to control modeled spike-time latency by bounding learned synaptic delays after training. The method derives per-layer, per-input latency bounds under an exponential-kernel assumption. On a ten-class Google Speech Commands subset, a four-layer network achieved 94.25% accuracy and 1,477.1198 ms average latency; this selected result is not an end-to-end deadline guarantee.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.