Learning of Artificial Neural Networks by Genetic Algorithms. | ||||
| MEJ- Mansoura Engineering Journal | ||||
| Article 7, Volume 35, Issue 1, March 2010, Page 21-33 PDF (695.41 K) | ||||
| Document Type: Research Studies | ||||
| DOI: 10.21608/bfemu.2020.123574 | ||||
 View on SCiNiTO | ||||
| Author | ||||
| Jamal Abdul Fatah M. Azzam* | ||||
| Department of Electrical Engineering, Faculty of Engineering, Mansoura University, Mansoura, Egypt | ||||
| Abstract | ||||
| Learning and evolution are two fundamental forms of artificial intelligence. There has been a great interest in combining learning and evolution with artificial neural networks (ANNs) in recent years. The training problem for feed forward neural networks is a nonlinear parameter estimation that can be solved by a variety of optimization techniques. Many researches in the literature on neural networks has focused on variants of gradient descent. The training of neural networks using such techniques is known to be a slow process, with more sophisticated problems not always performing significantly better In this paper a new proposed algorithm to learn the neural networks is introduced. This algorithm implements the effectiveness of the genetic evolution techniques to adjust the weights values of the feed forward neural networks. Simulation examples of the proposed algorithm produce optimal or suboptimal solutions in a small computation times. | ||||
| Keywords | ||||
| Artificial neural networks; Evolutionary computation; Genetic algorithms; Fitness function | ||||
|
Statistics Article View: 97 PDF Download: 172 |
||||
