标签:分类 super 一周 cluster strong 学习 ges regress clu
"A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E."
Example: playing checkers.
E = the experience of playing many games of checkers
T = the task of playing checkers.
P = the probability that the program will win the next game.
一个计算机程序从指定任务T,学习执行任务T的相关经验E,提高了执行任务的准确性P
比如下棋:
E(数据):下很多盘棋的经验
T(任务):下棋
P(准确性):下下一盘棋赢的概率
在监督学习中,会给予一个已知正确答案的输入数据集,找到数据集与正确答案之间的关系
输出结果是离散值,给输入数据分类
和监督学习相比,无监督学习没有给定正确输出结果,无监督学习并没有给定机器学习的方向,完全是凭数据集中数据与数据之间的内在关系来给数据分块(cluster),使每个块中数据与数据之间的差异最大值最小
所以也加聚类算法
标签:分类 super 一周 cluster strong 学习 ges regress clu
原文地址:http://www.cnblogs.com/xchaos/p/6535932.html