Both Netural Network and Genetic Algorithm are improving by imitiating intelligence of biology,and the research on combining them has become a hot topic at present.People hope to find an effient way to resolve problems by combining the virtue of both and make full use of them.By the combination people can understand the relationship of learning and evolution further.Based on the theoretical prediction and investment theory in the stock market,I propose a method of BP neural network modeling.Stock market is a nonlinear dynamic system,with its broad adaptability and learning ability,it gets a better prediction.The algorithm combined with BP algorithm is used to optimize the topological structure and weight values of multi-layer forward neutral network.In this paper,the program of improved GA optimizated BP network is designed by MATLAB. Weights optimization of BP network is an optimization problem,and the value is used by real number coding,with the MATLAB genetic algorithm toolbox, we can obtain a better prediction effect in the simulation. |