粗神经网络及其在股市预测中的应用  

Rough neural network model for stock market predication

作　　者：谢海燕[1] 赵连昌[1] 王德强[1] 

机构地区：[1]大连海事大学数理系,辽宁大连116026

出　　处：《大连海事大学学报》2002年第3期77-80,共4页Journal of Dalian Maritime University

基　　金：国家自然科学基金资助项目(19871007).

摘　　要：给出由粗神经元及一般神经元组成的前向粗神经网,用它预测上证指数.每个神经元是由一对神经元构成的.一般情形下,两个神经元用四边连接,而一个粗神经元和普通神经元用两边连接给出了误差后向传播算法.分析与计算表明,粗神经网络用于股市预测是可行的,结果也较准确.This paper describes a feedforward rough neural network model that consists of rough neurons and conventional neurons for prediction of the Shanghai Composite. Each rough neuron can be viewed as a pair of neurons. In general, two rough neurons in the network can be connected each other using four connections, while a rough neuron and a conventional neuron are connected by two connections. A back-propagation learning algorithm is given. Analyses and experiments illustrate that the rough network is available for stock market prediction.

关 键 词：粗神经网络 股市 预测 粗集理论 上证指数 

分 类 号：F832.5[经济管理—金融学] TP183[自动化与计算机技术—控制理论与控制工程]