Cargando…

Rosenblatt’s First Theorem and Frugality of Deep Learning

The Rosenblatt’s first theorem about the omnipotence of shallow networks states that elementary perceptrons can solve any classification problem if there are no discrepancies in the training set. Minsky and Papert considered elementary perceptrons with restrictions on the neural inputs: a bounded nu...

Descripción completa

Detalles Bibliográficos
Autores principales: Kirdin, Alexander, Sidorov, Sergey, Zolotykh, Nikolai
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9689667/
https://www.ncbi.nlm.nih.gov/pubmed/36359726
http://dx.doi.org/10.3390/e24111635