Title: Two-stage hybrid tuning algorithm for training neural networks in image vision applications

Authors: George A. Papakostas, Yiannis Boutalis, Sofoklis Samartzidis, Dimitrios A. Karras, Basil G. Mertzios

Addresses: Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece. ' Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece. ' Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece. ' Department of Automation, Chalkis Institute of Technology, Chalkis, Greece. ' Department of Automation, Laboratory of Control Systems and Comp. Intell., Thessaloniki Institute of Technology, Thessaloniki, Greece

Abstract: In the present paper a comparative study of two possible combinations of the Backpropagation (BP) and a Genetic Algorithm (GA), for Neural Networks training is performed. The performance of these approaches is compared to each other and to each algorithm incorporated separately in the training procedure. The construction of hybrid optimisation algorithms is originated from the need to manipulate and solve difficult optimisation problems by combining their advantages. The locality and globality behaviour of BP and GA is investigated by the presented hybrid structures, by applying them in five popular benchmark problems. In a second phase, the most efficient of these hybrid algorithms is used, in a typical pattern recognition task. It is concluded, that a more sophisticated structure based on the collaboration of two powerful optimisation algorithms can be used to train a typical neural network more efficiently.

Keywords: neural networks; backpropagation; genetic algorithms; GAs; hybrid tuning algorithms; image vision; training; optimisation.

DOI: 10.1504/IJSISE.2008.017775

International Journal of Signal and Imaging Systems Engineering, 2008 Vol.1 No.1, pp.58 - 67

Published online: 12 Apr 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article