The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 52-400
Full Name: Akram Mustafa
Position: Assistant Professor
Age: ON
Sex: Male
Address: jordan street 15, P.O.BOX 922283, 11192
Country: JORDAN
Tel: 00962795528616
Tel prefix:
Fax:
E-mail address: hamarchi@yahoo.com
Other E-mails:
Title of the Paper: Performance Evaluation of Artificial Neural Networks for Spatial Data Analysis
Authors as they appear in the Paper: Akram Moustafa, Ziad Alqadi and Eyad Shahroury
Email addresses of all the authors: hamarchi@yahoo.com,natalia_maw@hotmail.com,eyadmn73@hotmail.com
Number of paper pages: 10
Abstract: the artificial neural network training algorithm is implemented in MATLAB language. This implementation is focused on the network parameters in order to get the optimal architecture of the network that means (the optimal neural network is the network that can reach the goals in minimum number of training iterations and minimum time of training). Many examples were tested and it was shown that using one hidden layer with number of neuron equal to the square of the number of inputs will lead to optimal neural network by mean of reducing the number of training stages (number of training iterations) and thus the processing time needed to train the network.
Keywords: Artificial neural network (ANN), Back-propagation, training rate and training iteration (epochs), hidden layer, net simulation, multilayer perceptron (MLP).
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: Artificial Neural Networks
IP ADDRESS: 86.108.37.140
