摘要
为提高BP神经网络预测精度,基于深度学习理论提出一种深度信念网络(DBN)算法优化传统BP神经网络预测模型。该预测算法由多层限制玻尔兹曼机(RBM)组成,采用无监督学习算法训练参数,然后利用反向学习微调网络参数,进而优化BP神经网络的阈值和权值,通过训练模型求得最优解。实验表明,该预测模型克服了传统神经网络容易陷入局部最优以及函数拟合度不高的缺点,可有效提高交通流预测精度。
In order to improve the prediction accuracy of BP neural network,this paper,based on deep learning theory,puts forward adeep belief network(DBN)algorithm to optimize the traditional BP neural network prediction.This algorithm is composed of multi Re-stricted Boltzmann Machine(RBM),and it uses unsupervised learning algorithm to train the parameters.Then,it uses reverse learningto fine tune the network parameters and optimize the threshold and weight of BP neural network.This way can derive the optimal solutionthrough training.The experimental results show that the optimization model can overcome two shortcomings of traditional neural network:one is that traditional neural network tend to fall into local optimum and the other is that the function fitting degree remains low.There-fore,this model can effectively improve the prediction accuracy of traffic flow.
作者
孔繁辉
李健
Kong Fanhui;Li Jian(Research Center for Recyeling Economy and Enterprises Sustainable Development,Tianjin University of Technology,Tianjin 300384;Department of Management and Economics,Tianjin University,Tianjin 300072)
出处
《管理评论》
CSSCI
北大核心
2020年第3期300-306,共7页
Management Review
基金
教育部哲学社会科学研究重大课题攻关项目(15JZD021)。
关键词
交通流预测
深度学习
深度信念网络
BP神经网络
限制玻尔兹曼机
traffic flow prediction
deep learning
deep belief network
BP neural network
Restricted Boltzmann Machine
