Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/7152
Title: Novel neuronal activation functions for feedforward neural networks
Authors: Efe, Mehmet Önder
Keywords: activation functions
dynamical system identification
Levenberg-Marquardt algorithm
Issue Date: 2008
Publisher: Springer
Abstract: Feedforward neural network structures have extensively been considered in the literature. In a significant volume of research and development studies hyperbolic tangent type of a neuronal nonlinearity has been utilized. This paper dwells on the widely used neuronal activation functions as well as two new ones composed of sines and cosines, and a sinc function characterizing the firing of a neuron. The viewpoint here is to consider the hidden layer(s) as transforming blocks composed of nonlinear basis functions, which may assume different forms. This paper considers 8 different activation functions which are differentiable and utilizes Levenberg-Marquardt algorithm for parameter tuning purposes. The studies carried out have a guiding quality based on empirical results on several training data sets.
URI: https://doi.org/10.1007/s11063-008-9082-0
https://hdl.handle.net/20.500.11851/7152
ISSN: 1370-4621
1573-773X
Appears in Collections:Elektrik ve Elektronik Mühendisliği Bölümü / Department of Electrical & Electronics Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record

CORE Recommender

SCOPUSTM   
Citations

10
checked on Sep 23, 2022

WEB OF SCIENCETM
Citations

10
checked on Sep 24, 2022

Page view(s)

10
checked on Dec 26, 2022

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.