A SOFT-backpropagation algorithm for training neural networks

Loading...
Thumbnail Image

Date

2002-03

Journal Title

Journal ISSN

Volume Title

Type

Article

Publisher

IEEE

Series Info

Proceedings of the Nineteenth National Radio Science Conference;7522573

Scientific Journal Rankings

Abstract

The backpropagation (BP) algorithm is a one of the most common algorithms used in the training of neural networks. The single offspring technique (SOFT algorithm) is a new technique (see Likartsis, A. et al., Proc. 9th Int. Conf. on Tools with Artificial Intelligence, p.32-6, 1997; Yao, X., Proc. IEEE, vol.87, p.1425-47, 1999) of applying the genetic algorithm in the training of neural networks which reduces the training time as compared with the backpropagation algorithm. We introduce a new technique. This technique is a hybrid SOFT-BP algorithm where the SOFT-algorithm is applied first to obtain an initially good weight vector. This vector is introduced to the backpropagation algorithm, which improves the precession of the weight vector to reach an acceptable error limit. The results show an acceptable improvement in the training speed for the hybrid technique as compared with the individual backpropagation or SOFT algorithm. We also study the success ratio (how many times the algorithm succeeds in finding a solution to the total number of trials) for the new hybrid algorithm. A recommended range of the switching error limit at which to switch from the SOFT algorithm to the BP algorithm is suggested.

Description

Keywords

University for Modern Sciences and Arts, MSA University, October University for Modern Sciences and Arts, جامعة أكتوبر للعلوم الحديثة والآداب, Neural networks , Biological neural networks , Genetic algorithms , Switches , On the job training , Neurons INSPEC: Controlled Indexing backpropagation , neural nets , genetic algorithms INSPEC: Non-Controlled Indexing backpropagation , neural network training , single offspring technique , genetic algorithm , weight vector , success ratio

Citation

A. LIKARTSIS, LVLACHAVAS, L. H. TSOUKALAS, "A New Hybrid Neural-Genetic Methodology for Improving Learning", Proceeding of the 9th international conference on tools with artificial intelligence Aristotie University, pp. 32-36, 1997. Show Context Google Scholar 2. X. YAO, "Evolving Artificial Neural Networks", Proceedings of the IEEE, vol. 87, pp. 1425-1447, 1999. Show Context Google Scholar 3. DAVID E. GOLDBERG, "Genetic Algorithms in search optimization and machine learning" in , Addison Wesley, 1989. Show Context Google Scholar 4. MICHALEWICZ ZBIGNIEW, "Genetic Algorithms + Data Structures = Evolution Program" in , Heidelberg:Springer-Verlag, 1994. Google Scholar 5. SANKAR K. PAL, PAUL P. WANG, "Genetic Algorithms For Pattern Recognition" in , Robert B. Stern, 1996. Google Scholar 6. JAMES A. FREEMAN, M. SKAPURA DAVID, "Neural Networks: Algorithms Applications and Programming techniques" in , Addison Wesley, 1991. Show Context Google Scholar 7. G. LOONEY CARL, "Pattern Recognition Using Neural Networks" in , Oxford University Press, 1997. Show Context Google Scholar 8. Simon Haykin, "Neural Networks A Comprehensive Foundation" in , Printice-Hall, 1994. Show Context Google Scholar