The no-free-lunch theorems of supervised learning.

The no-free-lunch theorems promote a skeptical conclusion that all possible machine learning algorithms equally lack justification. But how could this leave room for a learning theory, that shows that some algorithms are better than others? Drawing parallels to the philosophy of induction, we point...

Descripción completa

Detalles Bibliográficos
Publicado en:Synthese Vol. 199; no. 3/4; pp. 9979 - 10016
Autores principales: Sterkenburg, Tom F., Grünwald, Peter D.
Formato: Artículo
Publicado: Springer Nature Dec2021
Materias:
Acceso en línea:Ver este registro en EBSCOhost