Abstract
A GA-based optimization method of fractional linear neural network (FNN) is proposed. Firstly, the GA is used to optimize the weight of fractional linear neural network. A solution near the global optimum will be found. Then the global optimum in the local area can be obtained with back propagation algorithm for the FNN to train the network based on the solution. The simulation results show that the GA-based new approach to optimize the fractional neural network is feasible and effective.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Zhang, S., Zhang, X., Wang, L., Ding, J., Liu, G.: Study on annual precipitation and runoff forecast based on artificial neural network in the upper reach of yellow river. China Rural Water and Hydropower 1, 41–44 (2005)
Wu, Q., Zhang, Q., Wa, J.: Application of ANN in weather forecast. Computer Engineering 31, 176–179 (2005)
Yang, G., Wang, S., Yan, Q.: Research of fractional linear neural network and its ability for nonlinear approach. Chinese Journal of computers 30(2), 189–199 (2007)
Goldberg, D.E.: Genetic algorithm in search optimization and machine learning. Addison-Wesley, Reading (1989)
Goldberg, D.E.: The design of innovation. Kluwer Academic Publishers, Massachusetts (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yang, G., Guo, L. (2011). GA-Based Optimization Approach of Fractional Linear Neural Network and Its Application. In: Chen, R. (eds) Intelligent Computing and Information Science. ICICIS 2011. Communications in Computer and Information Science, vol 134. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-18129-0_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-18129-0_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-18128-3
Online ISBN: 978-3-642-18129-0
eBook Packages: Computer ScienceComputer Science (R0)