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

International Journal of Signal and Imaging Systems Engineering

Volumn 1, Issue 1, 2008, Pages 58-67

  Papakostas, George A ^a   Boutalis, Yiannis ^a   Samartzidis, Sofoklis ^a   Karras, Dimitrios A ^b   Mertzios, Basil G ^c  

^a DEMOCRITUS UNIVERSITY OF THRACE   (Greece)

^b Chalkis Institute of Technology   (Greece)

^c ALEXANDER TECHNOLOGICAL EDUCATIONAL INSTITUTE OF THESSALONIKI   (Greece)

Author keywords

Backpropagation; BP; GAs; Genetic Algorithms; hybrid algorithms; neural networks

Indexed keywords

EID: 77954287987     PISSN: 17480698     EISSN: 17480701     Source Type: Journal    
DOI: 10.1504/IJSISE.2008.017775     Document Type: Article

References (22)

1. Coley, D.A. (2001) An Introduction to Genetic Algorithms for Scientists and Engineers, World Scientific Publishing, Singapore.
2. Cybenco, G. (1989) ‘Approximation by superpositions of a sigmoidal function’, Mathematics of Control, Signals and System, Vol. 2, pp.303–314.
3. Fahlman, S.E. (1988) An Empirical Study of Learning Speed in Back-propagation Networks, Technical Report, CMU-CS-88–162.
4. Haddadnia, J., Faez, K. and Ahmadi, M. (2003) ‘A fuzzy hybrid learning algorithm for radial basis function neural network with application in human face recognition’, Pattern Recognition, Vol. 36, pp.1187–1202.
5. Harpham, C., Dawson, C.W. and Brown, M.R. (2004) ‘A review of genetic algorithms applied to training radial basis function networks’, Neural Comput. and Applic., Vol. 13, pp.193–201.
6. Haykin, S. (1999) Neural Networks - A Comprehensive Foundation, 2nd ed., Prentice-Hall, India.
7. Haykin, S. (2000) ‘Adaptive digital communication receivers’, IEEE Communications Magazine, December, pp.106–114.
8. Hornik, K., Stinchcombe, M. and White, H. (1989) ‘Multilayer feedforward networks are universal approximators’, Neural Networks, Vol. 2, pp.359–366.
9. Kim, Y.K. and Ra, J.B., (1991) ‘Weight value initialization for improving training speed in the backpropagation network’, International Joint Conference on Neural Networks (IJCNN’91), Singapore, Vol. 3, pp.2396–2401.
10. Langlet, F., Abdulkader, H., Roviras, D., Mallet, A. and Castanie, F. (2001) ‘Comparison of neural network adaptive predistorsion techniques for satellite down links’, Proceedings of International Joint Conference on Neural Networks, Washington DC, pp.709–714.
11. Liang, H. and Dai, G. (1998) ‘Improvement of cascade correlation learning algorithm with an evolutionary initialization’, Information Sciences, Vol. 112, pp.1–6.
12. Looney, C.G. (1997) Pattern Recognition Using Neural Networks, Theory and Algorithms for Engineers and Scientists, Oxford University Press, USA.
13. Mitzias, D.A. and Mertzios, B.G. (2004) ‘A neural multiclassifier system for object recognition in robotic vision applications’, Measurement, Special Issue on Imaging Measurement Systems, Vol. 36, Nos. 3–4, pp.315–330.
14. Montana, D.J. and Davis, L. (1989) ‘Training feedforward neural networks using genetic algorithms’, Proceedings of International Conference on Artificial Intelligence, Detroit, Michigan, pp.762–767.
15. Nguyen, D. and Widrow, B. (1990) ‘Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights’, International Joint Conference on Neural Networks (IJCNN’90), San Diego, CA, pp.21–26.
16. Oukhellou, L. and Aknin, P. (1999) ‘Hybrid training of radial basis function networks in a partitioning context of classification’, Neurocomputing, Vol. 28, pp.165–175.
17. Papakostas, G.A., Karras, D.A., Mertzios, B.G. and Boutalis, Y.S. (2005) ‘An efficient feature extraction methodology for computer vision applications using wavelet compressed zernike moments’, ICGST International Journal on Graphics, Vision and Image Processing, Special Issue: Wavelets and Their Applications, Vol. SI1, pp.5–15.
18. Russo, A.P. (1991) ‘Constrained neural networks for recognition of passive sonar signals using shape’, IEEE Conf. on Neural Networks for Ocean Engineering, Washington DC, pp.69–76.
19. Szymanski, P.T., Lemmon, M. and Bett, C.J. (1998) ‘Hybrid interior point training of modular neural networks’, Neural Networks, Vol. 11, pp.215–234.
20. Thimm, G. and Fiesler, E. (1997) ‘High-order and multilayer perceptron initialization’, IEEE Transactions on Neural Networks, Vol. 8, No. 2, pp.349–359.
21. Trentin, T. and Gori, M. (2001) ‘A survey of hybrid ANN/HMM models for automatic speech recognition’, Neurocomputing, Vol. 37, pp.91–126.
22. Zhang Q. and Benveniste, A. (1992) ‘Wavelet networks’, IEEE Transactions on Neural Networks, Vol. 3, No. 6, pp.889–898.