Reproduce “Modeling the Repetition-based Recovering of Acoustic and Visual Sources with Dendritic Neurons” 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
Giorgia Dellaferrera, Toshitake Asabuki, Tomoki Fukai
The authors test whether a biologically inspired neural model can learn a recurring sound source across mixtures with different maskers. The model uses dendritic and somatic compartments and evaluates population responses to learned and unfamiliar probes. On synthesized sounds, two mixtures yield above-90% probe-classification AUC, while one is near chance. Unlike human performance, the model declines beyond its best range.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.