李群机器学习(LML)的学习子空间轨道生成理论及算法初探  

Orbits generated theory of learning subspace and its algorithm in Lie-Group machine learning (LML)

作　　者：陈凤[1] 李凡长[1] 

机构地区：[1]苏州大学计算机科学与技术学院,江苏苏州215006

出　　处：《苏州大学学报（自然科学版）》2007年第1期61-66,共6页Journal of Soochow University(Natural Science Edition)

基　　金：江苏省自然科学基金资助项目(BK2005027;BK2002040);苏州大学211基金资助项目(2118005)

摘　　要：给出了Lie群机器学习(LML)的学习子空间轨道生成格及相关的基本概念,包括李群机器学习中的样例数据集、轨道生成格理论及其算法,同时也给出了实例验证分析,与C4.5、N-Bayes算法在分类正确率上进行了比较,由此进一步证明了该理论的可行性以及算法的有效性.The orbits generated lattice of learning subspace in Lie-group machine learning （LML） and its corresponding basic conceptions are proposed, which include sample set in Lie-group machine learning, orbits generated lattices theory and algorithm. Synchronously, this paper analyzes the example and compares its results with those of the CA. 5 decision tree learning and N-Bayes algorithm, which shows that the new algorithm is much superior in validity of categorization, thus it can be believed that the theory is feasible and the algorithm is valid.

关 键 词：李群机器学习 学习子空间 轨道生成格 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]