Smaller nets may perform better: special transfer functions

Autor(en): Elsken, T
Stichwörter: Computer Science; Computer Science, Artificial Intelligence; FEEDFORWARD; feedforward neural nets; identification from input output relation; Neurosciences; Neurosciences & Neurology
Erscheinungsdatum: 1999
Herausgeber: PERGAMON-ELSEVIER SCIENCE LTD
Journal: NEURAL NETWORKS
Volumen: 12
Ausgabe: 4-5
Startseite: 627
Seitenende: 645
Zusammenfassung: 
In an earlier study we stated sufficient conditions on the transfer function f of a feedforward multilayered neural net such that the output on R-n defines the net up to trivial changes and smaller nets can have better performance on finite sets. Here we prove that 1/(1 e(-x)), tanh x, (1 - e(-x))/(1 e(-x)) and inv tan x satisfy these conditions. (C) 1999 Elsevier Science Ltd. All rights reserved.
ISSN: 08936080
DOI: 10.1016/S0893-6080(99)00014-3

Show full item record

Google ScholarTM

Check

Altmetric