Reproduce “Teasing Apart Architecture and Initial Weights as Sources of Inductive Bias in Neural Networks” 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
Gianluca Bencomo, Max Gupta, Ioana Marinescu, R. Thomas McCoy, Thomas L. Griffiths
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.