一种自适应遗传BP神经网络模型研究及应用

Study and Application of an Adaptive Genetic BP Neural Network Model

如何更有效地提高神经网络的收敛速度和收敛质量。基于遗传算法的全局搜索和BP神经网络局部精确搜索的特性,提出一种自适应遗传BP神经网络模型,该模型的主要算法是先采用一种自适应遗传算法优化BP网络初始权重,而后再进行BP网络的训练过程。最后并研究如何利用该模型进行三级跳远成绩预测。实验结果表明该方法优于传统BP算法,有利于提高网络的收敛性以及学习能力,可在一定程度上提高三级跳远成绩预测的准确率,具有一定的实用价值。

Based on the characteristics of the genetic algorithm and BP nerve network,the paper proposes an adaptive genetic BP neural network model. This model uses an adaptive genetic algorithms to optimize the BP network initial weight first, then carries out the BP network training process. Finally using this model to carry out the triple jump score prediction. The experimental result indicates that this method surpasses traditional BP algorithm, can improve the convergency and the learning capability of the network, and may make the triple jump score prediction more accurate.