A New Adaptive Genetic Neural Network Based Active Evolution

Neural network´s constructions and weights are one aspect of the basic questions. A kind of artificial neural network method based on an active evolution genetic algorithm is proposed. Introduce the algorithm´s basic idea. Active evolution genetic algorithm is combined the active evolution algorithm which is advantaged both overcoming the local optimized value and keeping rapidly convergence. Save time and space for the construction of new network, improve the output´s error precision and find the better way to solve how to build the network´s weights and structures at the beginning. The experiment results show that the algorithm is superior to simple genetic neural network algorithm with higher convergent speed, optimization and practical value of structures and weights, and improves network´s forecasting accuracy.