Reproduce “Input-dependent Neuromodulation Enhances Mixed-Signal Neuromorphic Hardware” 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
Aashman Mehta, AbdelQader AlKilany, Dan F. M. Goodman, Giacomo Indiveri, Melika Payvand
The authors demonstrate input-dependent computation in a physical spiking network by using an off-chip controller to adjust shared gains while a fixed recurrent reservoir processes inputs. On a five-versus-nine spoken-digit task, mean test accuracy across five hardware instances rises from 71.4% to 88.6%, an increase of 17.3 percentage points. The demonstration is limited to this task and remains partly host-run.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.