Optimized BP Neural Network Model Based on Niche Genetic Algorithm
According to the shortcomings of BP neural network model, such as slower convergence speed, entrapment in local optimum, unstable network structure etc., and an improved BP neural network model based on niche genetic algorithm (NGA-BP) was presented. The proposed model first makes full use of the global searching ability of genetic algorithm and the nonlinear reflection ability and the association learning ability of BP neural network to optimize the initial connection weights and thresholds of the neural network by means of selection operation, crossover operation, mutation operation and niche pass, and then adopts BP algorithm to train network, which can effectively solve the problems of BP network about unreasonable initial value and network nonconvergence, and improve the convergence speed and the stability of network. The experimental results show that the model is more feasible and effective than the traditional methods.
KeywordsBP neural network Niche genetic algorithms Nonlinear reflection Genetic operations
This work is supported by the Foundation and Frontier Technologies Research Plan Projects of Henan Province of China (No. 102300410266 and No. 122300410287) and a grant from the Ph.D. Research Funded Projects of Zhengzhou University of Light Industry (No. 2010BSJJ038). In addition, this work also received guidance from Huang De-Shuang who is a distinguished professor in Henan Province.
- 5.Wang J-Z, Wang J-J, Zhang Z-G (2011) Forecasting stock indices with back propagation neural network. Expert Syst Appl 38:14346–14355Google Scholar
- 9.Li H, Zhu H (2011) Research on timetabling problem based on niche genetic algorithm. Chin J Comput Eng 37:194–196Google Scholar
- 10.Fayek MB, Darwish NM, Ali MM (2010) Context based clearing procedure a niching method for genetic algorithm. J Adv Res 1:301–307Google Scholar