The week's pick
Reseach Article
Optimum Architecture of Neural Networks lane following system
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 42 - Number 12 |
| Year of Publication: 2012 |
| Authors: Imen Klabi, Afef Benjemmaa, Mohamed Slim Masmoudi, Mohamed Masmoudi |
10.5120/5748-7954
|
Imen Klabi, Afef Benjemmaa, Mohamed Slim Masmoudi, Mohamed Masmoudi . Optimum Architecture of Neural Networks lane following system. International Journal of Computer Applications. 42, 12 ( March 2012), 41-46. DOI=10.5120/5748-7954
Abstract
Recently, neural networks have demonstrated their ability to achieve excellent performance for the control of mobile robots. In fact, the recourse of this control method by learning has become a necessity because control systems obtain then, proceed by collecting empirical data, storing and removing the knowledge contained in it and using this knowledge to respond to new situations. However, the problem of choosing an optimal number of hidden layers as well as choosing neurons per layer is very critical for these networks. So here we propose to determine the settings for the optimum architecture of neural network. In the course of our experiments, we have shown that the error of learning as well as the one of the validation provides a satisfactory criterion for the optimization of network architecture.
References
- Sana Ben Romdhane, 2010, « Robots d'assistance pour les personnes handicapées : commande linéarisante par retour d'état et neuronale d'un système holonome à mise en position continue» Mastère, INSAT.
- Mark Buplawsky et Michal Bialko, May 2008, « Implementation of Parallel Fuzzy Logic Controller in FPGA Circuit for Guiding Electric Wheelchair », Article, Department of Electronics and Computer Science, Koszalin University of Technology, Koszalin, Poland.
- Hoang T. Trieu et Hung T. Nguyen, August 2008, « Advanced obstacle avoidance fora laser based wheelchair using optimised bayesian neural networks », international IEEE EMBS conference, British Coulombia, Canada.
- Nghia Nguyen et Hung T. Nguyen, septembre 2009, « Robuste Multi-variables strategy and its application to a powered wheelchair », international IEEE EMBS conference, Minneapolis, Minnesota, USA.
- Ludovic Arnold, Hélène Paugam-Mois Y et Michèle Sebag, 2010, « optimisation de la Topologie pour les Réseaux de Neurones Profonds », Article, Université Paris-Sud et Université de Lyon.
- Mohamed Slim Masmoudi, avril 2008, « Conception et implémentation de systèmes intelligents appliqué au stationnement d'un véhicule-robot », thèse de Doctorat, ENIS.
- Fei Jiang, Decembre 2009, «Optimisation de la Topologie de Grand s Réseaux de Neurones », these de Doctorat, Université Paris-SUD.
- J. Amini, Decembre 2008, «Optimum Learning Rate in Back-propagation Neural Network for classificationof Satellite Images (IRS-1D) », Article, Scientia Iranica, vol. 15, NO. 6, PP. 558-567, Sharif university of Technology.
Index Terms
Keywords