摘要
在以1∶1数字学习方式为主的自主学习模式下存在相关专业多学位识别的问题。针对该问题,建立了一种使用遗传算法和BP神经网络的多学位识别机制。该机制根据问题的特点,采用遗传算法产生样本群体,并用遗传算法确定神经网络模型的参数,通过神经网络自适应学习和训练,找出输入和输出的关系,从而达到多学位识别的目的。实验验证了该方法的有效性。
The genetic algorithm optimization back-propagation BP neural network decision-making mechanism was presented in order to overcome the shortcoming of the independent study model based on the digital technology supported learning that can't identify a number of degrees. According to its feature, the genetic algorithm is adopted to pro- duce sample groups and determine parameters of the neural network model. The relationship between input and outPut has been identified during adaptive learning and training of the neural network, so as to achieve the purpose of identification of multi-degree. It validates the proposed approach by experiments.
出处
《计算机科学》
CSCD
北大核心
2009年第10期253-255,共3页
Computer Science
基金
西华师范大学校启动基金项目(06B012)资助
关键词
遗传算法
BP神经网络
数字学习
多学位识别
Genetic algorithm, BP neural network, Digital technology supported learning, Identification of multi-degree