One small step for a man
One Giant leap for the mankind

There is no wealth like Knowledge
                            No Poverty like Ignorance
Journal of Emerging Trends in Computing and Information Sciences Logo

Journal of Emerging Trends in Computing and Information Sciences >> Call for Papers Vol. 8 No. 3, March 2017

Journal of Emerging Trends in Computing and Information Sciences

Analysis of Various Artificial Neural Networks used for Function Approximation

Full Text Pdf Pdf
Author Akram A. Mustafa
ISSN 2079-8407
On Pages 21-24
Volume No. 8
Issue No. 1
Issue Date February 1, 2017
Publishing Date February 1, 2017
Keywords Linear neural network, feed-forward neural networks, activation function, training function, MatLab M-code.


Several neural network structures is testing to solve function approximation problem with different outputs. In spite of the simple way to define the weights for linear neural networks it was shown that using feed-forward neural networks with at least one hidden layer leads to better performance (shortest training time and less number of training iterations), with keeping constant value for the mean square error. The difficulty of selecting the suitable weights for feed-forward neural networks can be solved using computational programming tools such as MatLab (M-code) and thus achieving high performance as shown through our experimental results. Therefore, in this paper, I used the linear ANN and it shown that it is better to use it hen assigning the accurate weights to the network, but if all weights starts with some initial values, it would be better to use feed-forward backpropagation ANN.

    Journal of Computing | Call for Papers (CFP) | Journal Blog | Journal of Systems and Software | ARPN Journal of Science and Technology | International Journal of Health and Medical Sciences | International Journal of Economics, Finance and Management     
© 2015 Journal of Computing