Reproduce “NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings” 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
Hanrui Lyu, Baiyuan Chen, Tianshu Tan, Matthew R. Whiteway, Maxwell D. Melin, Ji Xia, Linyang He, Bradly C. Stadie and 3 more
NeuroLens maps changing neural populations into a shared latent space and predicts future latents to support decoding across recording days. It uses calibration features to represent variable neuron sets, then trains a temporal predictor. On 14 held-out future mouse-task days, gradient-based adaptation achieved 0.83 choice balanced accuracy versus 0.64 for causal NDT; this does not establish what caused neural changes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.