摘要
针对目前神经网络在实际应用中,网络结构难以确定以及网络极易陷入局部解问题,用遗传算法优化神经网络的连接权和网络结构,并在遗传进化过程中采取保留最佳个体的方法,建立基于遗传算法的神经网络模型,实例研究结果表明该方法可以取得较高的预测精度.
For overcoming difficulties in application of the method of BP neural network,this paper proposed to optimize the neural network structure and connection weights by means of genetic algorithm whilst to reserve the best individual in evolution process,so that to build up a genetic algorithms Neural Networks model.The result of study indicates that this method can gain a higher forecasting precision.
出处
《数学的实践与认识》
CSCD
北大核心
2010年第20期54-58,共5页
Mathematics in Practice and Theory
关键词
短期气候预测
神经网络
遗传算法
short-term climate prediction
neural network
genetic algorithms
