Reproduce “Neuromorphic Wireless Split Computing with Multi-Level Spikes” 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
Dengyu Wu, Jiechen Chen, Bipin Rajendran, H. Vincent Poor, Osvaldo Simeone
The authors study wireless split computing for multi-level spiking neural networks, comparing digital and analog transmission over OFDM. Multi-level spikes encode a quantized payload alongside timing, and the best payload depends on channel quality and OFDM symbols. On centralized DVS128 Gesture with T = 4, accuracy rises from 92.33% to 96.40% as payload grows from 0 to 8 bits; this does not establish the gain over wireless links.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.