A Critical Analysis of the Theoretical Framework of the Extreme Learning Machine
Machine Learning
2024-06-26 v1 Neural and Evolutionary Computing
Abstract
Despite the number of successful applications of the Extreme Learning Machine (ELM), we show that its underlying foundational principles do not have a rigorous mathematical justification. Specifically, we refute the proofs of two main statements, and we also create a dataset that provides a counterexample to the ELM learning algorithm and explain its design, which leads to many such counterexamples. Finally, we provide alternative statements of the foundations, which justify the efficiency of ELM in some theoretical cases.
Keywords
Cite
@article{arxiv.2406.17427,
title = {A Critical Analysis of the Theoretical Framework of the Extreme Learning Machine},
author = {Irina Perfilievaa and Nicolas Madrid and Manuel Ojeda-Aciego and Piotr Artiemjew and Agnieszka Niemczynowicz},
journal= {arXiv preprint arXiv:2406.17427},
year = {2024}
}