Reproduce “Learning Task-Agnostic Motifs to Capture the Continuous Nature of Animal Behavior” 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
Jiyi Wang, Jingyang Ke, Bo Dai, Anqi Wu
MCD represents mouse behavior as a shared library of movement motifs whose contributions can change over time and overlap, rather than assigning each moment one discrete label. It learns motifs from behavioral transitions and combines them into action tendencies. On free-moving mouse data, MCD leads baselines in held-out label decoding and mismatch discrimination; this does not establish neural mechanisms.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.