Reproduce “A Critical Analysis of the Theoretical Framework of the Extreme Learning Machine” 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
Irina Perfilievaa, Nicolas Madrid, Manuel Ojeda-Aciego, Piotr Artiemjew, Agnieszka Niemczynowicz
The paper examines whether Extreme Learning Machines, which randomly fix hidden-layer connections and solve output weights analytically, guarantee exact fitting. It critiques the proof and tests a constructed 400-example dataset: sigmoid runs with 400 or 50 units, and ReLU with 400, fail visually, while ReLU with 8,000 reproduces all examples. The guarantee is unsupported, not universally disproved.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.