摘要
在大数据、人工智能的背景下,神经网络算法被广泛的应用和普及,风险预测问题成为人们关注的热点,BP神经网络算法是用于解决预测问题效果最好的算法之一,但传统的BP神经网络算法在隐含层权值选择过程具有一定的局限性,会影响算法预测的效率和精度。针对这种情况,提出了改进的BP神经网络算法,利用遗传算法和BP神经网络算法相结合,提升算法的预测效率和预测精度。首先,分析传统BP神经网络算法流程及不足;其次,利用遗传算法优化BP神经网络算法;最后,提出改进的BP神经网络算法执行流程,并以食品价格数据进行对比分析。通过实验分析结果可知,相对于传统的BP神经网络算法,该方法在预测过程中可以提高预测效率、提升预测精度。
In the context of big data and artificial intelligence,neural network algorithms are widely used and popularized.Risk prediction has become a hot topic of concern. BP neural network algorithm is one of the best algorithms for solving prediction problems,but the traditional BP neural network algorithm has certain limitations in the hidden layer weight selection process,which will affect the efficiency and accuracy of algorithm prediction. In view of this situation,an improved BP neural network algorithm is proposed,which uses a combination of genetic algorithm and BP neural network algorithm to improve the prediction efficiency and prediction accuracy of the algorithm. Firstly,the traditional BP neural network algorithm process and shortcomings are analyzed. Second,genetic algorithm is used to optimize the BP neural network algorithm. Finally an improved BP neural network algorithm execution process is proposed,and food price data is compared and analyzed. According to the experimental analysis results,compared with the traditional BP neural network algorithm,this method can improve the prediction efficiency and improve the prediction accuracy in the prediction process.
作者
邬希可
WU Xike(School of Business Administration,South China University of Technology,Guangzhou 510000)
出处
《计算机与数字工程》
2022年第10期2276-2279,2344,共5页
Computer & Digital Engineering
关键词
神经网络
BP神经网络算法
遗传算法
预测
neural network
BP neural network algorithm
genetic algorithm
prediction
