Influence activation function in approximate periodic functions using neural networks
Other Title(s)
تأثير دالة الاستثارة في تقريب الدوال الدورية باستخدام الشبكات العصبية
Joint Authors
Jabir, Ala Kamil
Tawfiq, Lama Naji Muhammad
Source
Ibn al-Haitham Journal for Pure and Applied Science
Issue
Vol. 27, Issue 1 (30 Apr. 2014), pp.306-313, 8 p.
Publisher
University of Baghdad College of Education for Pure Science / Ibn al-Haitham
Publication Date
2014-04-30
Country of Publication
Iraq
No. of Pages
8
Main Subjects
Abstract EN
The aim of this paper is to design fast neural networks to approximate periodic functions, that is, design a fully connected networks contains links between all nodes in adjacent layers which can speed up the approximation times, reduce approximation failures, and increase possibility of obtaining the globally optimal approximation.
We training suggested network by Levenberg-Marquardt training algorithm then speeding suggested networks by choosing most activation function (transfer function) which having a very fast convergence rate for reasonable size networks.
In all algorithms, the gradient of the performance function (energy function) is used to determine how to adjust the weights such that the performance function is minimized, where the back propagation algorithm has been used to increase the speed of training.
American Psychological Association (APA)
Tawfiq, Lama Naji Muhammad& Jabir, Ala Kamil. 2014. Influence activation function in approximate periodic functions using neural networks. Ibn al-Haitham Journal for Pure and Applied Science،Vol. 27, no. 1, pp.306-313.
https://search.emarefa.net/detail/BIM-795006
Modern Language Association (MLA)
Tawfiq, Lama Naji Muhammad& Jabir, Ala Kamil. Influence activation function in approximate periodic functions using neural networks. Ibn al-Haitham Journal for Pure and Applied Science Vol. 27, no. 1 (Apr. 2014), pp.306-313.
https://search.emarefa.net/detail/BIM-795006
American Medical Association (AMA)
Tawfiq, Lama Naji Muhammad& Jabir, Ala Kamil. Influence activation function in approximate periodic functions using neural networks. Ibn al-Haitham Journal for Pure and Applied Science. 2014. Vol. 27, no. 1, pp.306-313.
https://search.emarefa.net/detail/BIM-795006
Data Type
Journal Articles
Language
English
Notes
Includes appendices : p. 311-312
Record ID
BIM-795006