遗传算法优化BP神经网络研究

Study on Genetic Algorithm Optimization and BP Neural Networks

研究了遗传算法优化BP神经网络隐含层节点数，从而使BP神经网络具有更快的收敛性和更强的学习能力．

The Artificial Neural Net mind, possesses the strong learning （ANN） ＇s a way to deal with the information by simulating the human being＇s functionality and nonlinear reflection ability. BP nerve network is the core part of the feed - forward neural networks, but there are also some problems such as it is low rate of convergence, is lia- ble to trap in minimum value, and is difficult to decide the number of hidden layer nodes. Using the global search mechanism of the genetic algorithm, this article studies the genetic algorithm optimization and BP neural networks hidden layer nodes, to make the BP neural networks own faster astringency and stronger learning functionality.