Reproduce “Stochastic Gradient Based Extreme Learning Machines For Online Learning of Advanced Combustion Engines” 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

Vijay Manikandan Janakiraman, XuanLong Nguyen, Dennis Assanis

The SG-ELM updates an Extreme Learning Machine’s output weights one observation at a time, avoiding OS-ELM’s recursive least-squares covariance update. Its Lyapunov analysis establishes prediction-error convergence under stated gain conditions, with true-parameter recovery requiring sufficiently rich inputs. In HCCI tests at 1,800 rpm, it trained faster and improved multi-step error, but not one-step accuracy; findings do not establish deployment.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.