A method to resolve the overfitting problem in recurrent neural networks for prediction of complex system's behavior

Mahdaviani, K; Mazyar, H; Majidi, S; Saraee, MH

Abstract

In this paper a new method to resolve the
overfitting problem for predicting complex systems'
behavior has been proposed. This problem occurs when a
neural network loses its generalization. The method is
based on the training of recurrent neural networks and
using simulated annealing for the optimization of their
generalization. The major work is done based on the idea
of ensemble neural networks. Finally the results of using
this method on two sample datasets are presented and the
effectiveness of this method is illustrated.

Citation

Mahdaviani, K., Mazyar, H., Majidi, S., & Saraee, M. (2008, June). A method to resolve the overfitting problem in recurrent neural networks for prediction of complex system's behavior. Presented at IEEE World Congress on Computational Intelligence / IEEE International Joint Conference on Neural Networks, Hong Kong, China

• Presentation Conference Type: Other
• Conference Name: IEEE World Congress on Computational Intelligence / IEEE International Joint Conference on Neural Networks
• Conference Location: Hong Kong, China
• Start Date: Jun 1, 2008
• End Date: Jun 6, 2008
• Publication Date: Jan 1, 2008
• Deposit Date: Oct 26, 2011
• Book Title: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)
• DOI: https://doi.org/10.1109/IJCNN.2008.4634332
• Publisher URL: http://dx.doi.org/10.1109/IJCNN.2008.4634332
• Additional Information: Additional Information : Print ISBN: 978-1-4244-1820-6; Event Type : Conference