Reproduce “Deep Learning Architectures for FSCV, a Comparison” 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
Thomas Twomey, Leonardo Barbosa, Terry Lohrenz, P. Read Montague
The authors compare neural-network architectures for estimating neurotransmitter concentrations from fast scan cyclic voltammetry traces using probe-held-out in-vitro data. For dopamine, mean RMSE was 215.696 nM for InceptionTime and 276.755 nM for MLP_wide; InceptionTime had the best median error. MLP_wide was less affected by tested artificial noise, but results do not establish clinical performance or robustness to in-vivo noise.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.