摘要
神经网络控制系统通常会面临多种选择,如样本的训练方式、神经网络的算法等,不好的选择会降低预测率。BP(Back Propagation)神经网络库存控制系统融合多种库存控制技术,利用BP算法对学习的精度和收敛的速度进行改进,能比较精确地预测库存。讨论了有关BP神经网络的算法及算法改进等问题,以品牌服装库存控制为例,提出用神经网络的多层感知器实现库存融合控制。
There are a number of choices for neural network control system, such as the training method of the sample, the algorithm of the neural network. It will reduce the forecast rate if you make a bad choice. BP（Back Propagation） neural network inventory control system integrates a variety of inventory control techniques, it can use BP algorithm to improve the accuracy of the studies and the speed of the convergence, it can also calculate inventory more accurately.This paper discusses the algorithm of the neural network and the improvement of the algorithm. Take the case of branded clothing inventory control, realize the control of inventory integrating by using the multilayered perceptron of neural network.
关键词
神经网络
预测
多层感知器
BP算法
库存
neural network
forecast
multilayer percePtron
BP algorithm
stock
