混合型多概念获取系统的设计与实现

DESIGN AND IMPLEMENTATION OF A HYBRID MULTI CONCEPTS ACQUISITION SYSTEM

本文主要描述了一个增量式混合型多概念获取系统ＨＭＣＡＳ．它提出了一个基于概率论的符号学习与神经网络学习相结合的学习算法，能从隶属于某个概念集的实例集中归纳出满足用户精度要求的、以混合型判定树表示的概念描述．在ＨＭＣＡＳ中，符号学习与神经网络学习具有结合紧密和转换灵活等特点，具有较高的学习效率和较强的归纳能力以及增量学习能力．ＨＭＣＡＳ的神经网络学习可选择ＢＰ网络或ＦＴＡＲＴ网络。

This paper describes an incremental hybrid multi concept acquisition system HMCAS.It puts forward a concept learning algorithm based on the probability theory,which is a hybrid of symbolic method and neural network.HMCAS conjoins the symbolic and neural network approaches tightly,and it has an incremental learning mechanism.Users can select BP or FTART approach to accomplish neural network learning.Its inference mechanism has the ability of hybrid decision tree inference.