基于改进遗传算法进化神经网络
温秀兰;徐永祥
【期刊名称】《内蒙古工业大学学报(自然科学版)》 【年(卷),期】2003(022)002
【摘要】本文提出一种新颖的基于实数编码的改进遗传算法用于神经网络的训练,该算法采用基于代沟最小的代选择模型,选用BLX-α混合交叉算子,算法简单、鲁棒性强,优化兆效率高.并将该神经网络应用于非线性系统预测,仿真结果证实该方法是快速有效的.%In this paper a novel real-coded improved genetic algorithm (GA) of training neural network is proposed.That is,A generation-alternation model based the Minimal Generation Gap (MGP) and blend crossover operators (BLX-α) are employed.Compared with conventional
methods,it
has
the
advantages
of
simplify
algorithms,strong robustness and high optimization efficiency.Then forecasting nonlinear system using feed-forward neural network is present.Simulation shows the method is rapid and effective. 【总页数】4页(131-134)
【关键词】遗传算法;神经网络;非线性预测 【作者】温秀兰;徐永祥
【作者单位】内蒙古工业大学机械学院,内蒙古,呼和浩特,010062;东南大学仪器科学系,南京,210096;内蒙古工业大学机械学院,内蒙古,呼和浩特,010062 【正文语种】中文 【中图分类】TH164
基于改进遗传算法进化神经网络



