Reproduce “Engram Memory Network: Brain-Inspired Prototype Explanations” 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
Hyunjun Kim, Myoung Hoon Ha
EMN uses memory activations to select training examples while iteratively refining visual and categorical representations for image reconstruction and classification. It stores visual and label memories, updating their activation weights through feedback. Across five datasets, EMN reports a 17.06% average improvement in visual-similarity measures over ProtoPFormer, but these proxies do not establish faithful explanations or human validation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.