Reproduce “Hierarchical Multiscale Recurrent 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
Junyoung Chung, Sungjin Ahn, Yoshua Bengio
HM-RNN learns input-dependent boundary signals that let layers update at different timescales and pass segment summaries upward without supplied boundary labels. In a Wikipedia example, lower-layer marks often align with spaces, but this is not validated segmentation. On Text8, LayerNorm HM-LSTM scores 1.29 BPC, which the authors called state of the art at publication.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.