CAJ | 학술논문

根据实际应用中神经网络训练样本通常具有内在特征和规律性,提出一种基于样本自组织聚类的BP神经网络预测模型.通过自组织竞争网络的聚类特征,改善样本训练对BP网络性能的影响.BP神经网络采用收敛速度较快和误差精度较高的动量-自适应学习速率调整算法.并通过基于这种模型的空气质量预测实验,表明基于样本自组织聚类的BP神经网络预测模型首先会提高收敛速度,其次会减少陷入局部最小的可能.提高预测精度.
근거실제응용중신경망락훈련양본통상구유내재특정화규률성,제출일충기우양본자조직취류적BP신경망락예측모형.통과자조직경쟁망락적취류특정,개선양본훈련대BP망락성능적영향.BP신경망락채용수렴속도교쾌화오차정도교고적동량-자괄응학습속솔조정산법.병통과기우저충모형적공기질량예측실험,표명기우양본자조직취류적BP신경망락예측모형수선회제고수렴속도,기차회감소함입국부최소적가능.제고예측정도.
Train samples usually have inherent characteristic and regularity according to the neural network in practical applica-tion.This paper presents a BP neural network predicting model baaed on samples self-organizing clustering.Tha effect of samples training on BP neural network performance with the clustering characteristic of self-organizing competitive network is improvod.BP neural network using adaptive learning rate momentum algorithm has fast convergence rate and high error precision.And according to the air quality forecast experiment based on this kind of model,the BP neural network predicting model based on samples self-organizing clustering improves convergence rate at first,secondly reduces the possibility of getting into local minimum,and improves the prediction accuracy.