基于模糊理论扩充的归纳学习方法和思想  

Inductive Learning Methods and Ideas Based on Fuzzy Theory Expansion

作　　者：陈建祥 肖卫东[2] 宋峻峰[2] 

机构地区：[1]北京1092信箱,北京100034 [2]国防科技大学管理科学与工程系,湖南长沙410073

出　　处：《计算机工程与科学》2006年第4期63-65,118,共4页Computer Engineering & Science

基　　金：国家自然科学基金资助项目(60172012)

摘　　要：归纳学习是机器学习最重要、最核心也是最成熟的一个分支,但在应用归纳学习所获得的知识以及改进归纳学习算法等方面存在着很多传统方法难以解决的问题。本文从归纳学习的本质———归纳依赖于数据间的相似性出发,尝试将能够较好地定量反映数据间相似性程度的模糊理论应用到归纳学习中去,为归纳学习和机器学习找出一个新的研究方法和思路。Inductive learning is one of the most important, the corest and the maturest branches in machine learning, but for using the knowledge acquired by learning and improving inductive learning algorithms, there are a lot of problems that are hard to solve using traditional methods. In this paper, the essence of inductive learning, i. e. induction depending on the similarity of data, is considered as the starting point. Fuzzy theory, which can quantitatively reflect the similarity among data, is introduced into inductive learning. This introduction gives a new method and idea for inductive learming.

关 键 词：归纳学习 机器学习 向量空间 相似度 距离 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391[自动化与计算机技术—控制科学与工程]