The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 31-699
Full Name: Mohamed Ettaouil
Position: Professor
Age: ON
Sex: Male
Address: Department of Mathematics and Computer science Faculty of Science and Technology of Fez box 2202
Country: MOROCCO
Tel: +21233374871 and +21212042096
Tel prefix:
Fax:
E-mail address: mohamedettaouil@yahoo.fr
Other E-mails: yghanou2000@yahoo.fr
Title of the Paper: Neural architectures optimization and Genetic algorithms
Authors as they appear in the Paper: mohamed ettaouil and youssef ghanou
Email addresses of all the authors: mohamedettaouil@yahoo.fr yghanou2000@yahoo.fr
Number of paper pages: 12
Abstract: Abstract: The artificial neural networks (ANN) have proven their efficiency in several applications: pattern recognition, voice and classification problems. The training stage is very important in the ANN's performance. The selection of the architecture of a neural network suitable to solve a given problem is one of the most important aspects of neural network research. The choice of the hidden layers number and the values of weights has a large impact on the convergence of the training algorithm. In this paper we propose a mathematical formulation in order to determine the optimal number of hidden layers and good values of weights. To solve this problem, we use genetic algorithms. The numerical results assess the effectiveness of the theorical results shown in this paper and computational experiments are presented, and the advantages of the new modelling.
Keywords: Artificial neural networks (ANN), Non linear optimization, Genetic algorithms, Supervised Training, Feed forward neural network.
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 41.249.59.135
