RT journal article
T1 A critical analysis of the theoretical framework of the Extreme Learning Machine
A1 Perfilieva, Irina
A1 Madrid Labrador, Nicolás Miguel
A1 Ojeda Aciego, Manuel
A1 Artiemjew, Piotr
A1 Niemczynowicz, Agnieszka
A2 Matemáticas
K1 Extreme Learning Machine
K1 Feed-forward neural network
K1 Generalized inverse Moore-Penrose matrix
K1 Pseudo-inverse matrix
AB 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.
PB Elsevier
SN 0925-2312
YR 2025
FD 2025-03-25
LK http://hdl.handle.net/10498/38430
UL http://hdl.handle.net/10498/38430
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 10-may-2026