2026-05-30T08:13:25Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/402472026-02-03T11:18:53Zcom_10630_2254col_10630_37953

A critical analysis of the theoretical framework of the Extreme Learning Machine. Perfilieva, Irina Madrid-Labrador, Nicolás Miguel Ojeda-Aciego, Manuel Artiemjew, Piotr Niemczynowicz, Agnieszka Aprendizaje automático (Inteligencia artificial) Redes neuronales (Informática) Matrices (Matemáticas) Extreme learning machine Feed-forward neural network Pseudo-inverse matrix Generalized inverse Moore-Penrose matrix https://openpolicyfinder.jisc.ac.uk/id/publication/15862 Despite several successful applications of the Extreme Learning Machine (ELM) as a new neural network training method that combines random selection with deterministic computation, we show that some fundamental principles of ELM lack a rigorous mathematical basis. In particular, we refute the proofs of two fundamental claims and construct datasets that serve as counterexamples to the ELM algorithm. Finally, we provide alternative claims to the basic principles that justify the effectiveness of ELM in some theoretical cases. 2025-10-15T10:54:41Z 2025-10-15T10:54:41Z 2025-01-02 journal article AM Irina Perfilieva, Nicolás Madrid, Manuel Ojeda-Aciego, Piotr Artiemjew, Agnieszka Niemczynowicz: A critical analysis of the theoretical framework of the Extreme Learning Machine. Neurocomputing 621: 129298 (2025) https://hdl.handle.net/10630/40247 10.1016/j.neucom.2024.129298 eng embargoed access application/pdf Elsevier