Kamran Jamalzadeh - M. Sc. Student, Department of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.
Gholamreza Akbarizadeh - Assistant Professor, Department of Electrical Engineering, Faculty of Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.

In training neural network, training method selection has an important role on network performance. Particle swarm optimization is a mathematical calculation procedure for optimizing every continuous real function, which is taken from the social behavior of alive organisms. In this paper, a new evolutionary neural networks training method is presented. We show that this trained neural network is useful for image compression. The results show that this method is more effective than the other similar method.

neural networks, particle swarm optimization, image compression