基于神经网络集成技术构建IDSS知识库的研究  

Research of constructing IDSS knowledge based on neural network ensemble

作　　者：高广耀[1] 王世卿[1] 

机构地区：[1]郑州大学信息工程学院,河南郑州450052

出　　处：《计算机工程与设计》2005年第8期2083-2085,2173,共4页Computer Engineering and Design

摘　　要：神经网络集成通过训练多个神经网络并将其结果进行合成,可以显著地提高学习系统的泛化能力,有助于工程技术人员利用神经网络技术来解决真实世界中的问题。在分析智能决策支持系统(IDSS)目前面临问题基础上,论述了神经网络集成实现的方法,对神经网络集成技术在构建IDSS知识库中的应用进行了研究,并成功进行了实现。Through training a finite number of neural networks and then combining their results, neural network ensemble can significantly improve the generalization ability of learning system and is also helpful for common engineers to solve real-world problems using neural network techniques. The difficulty was introduced that IDSS faces at present briefly, and then the methods were described to realize neural network ensemble, and finally the application of neural network ensemble on constructing IDSS knowledge base was studied and implemented successfully.

关 键 词：IDSS 专家系统 神经网络 神经网络集成 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]