智能混合系统研究综述  

A RESEARCH SURVEY FOR INTELLIGENT HYBRID SYSTEMS

作　　者：贵忠华[1] 刘振凯[2] 

机构地区：[1]西北工业大学,西安710072 [2]西安交通大学,西安710049

出　　处：《信息与控制》2000年第1期59-64,共6页Information and Control

基　　金：航空自选课题基金

摘　　要：作为人工智能的两个主要研究方向 ,专家系统和神经网络在过去的几十年中均取得了很大的成功 ,但二者又存在一些各自的缺陷 ,不能单独解决一些复杂的工程实际问题 .因此 ,智能混合系统就成为当今人工智能研究领域中的一个非常重要且具有很大实用价值和广阔发展前景的研究领域 .本文分析比较了专家系统和神经网络的基本特点 。Expert systems and neural networs are two principal developing fields of artificial intelligence. They have made both great progress and success in the last decades. However, each of them has its own drawbacks and can not deal with complex engineering problems. So, it becomes a very important research field with great practical values and broad developing prospects to research on intelligent hybrid systesm based on neural networks and expert systems. In this paper, the characteristics of expert systems and neural networks are analyzed, a survey of intelligent hybrid systems is made and some problems are proposed.

关 键 词：人工智能 专家系统 神经网络 智能混合系统 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]