【光能蜗牛的人工智能之旅】week1 : 5.What is M

What is Machine Learning?
Two definitions of Machine Learning are offered. Arthur Samuel described it as: "the field of study that gives computers the ability to learn without being explicitly programmed." This is an older, informal definition.
什么是机器学习？
提到了两种机器学习的定义，第一种是比较久远一些的不太正式的定义，Arthur Samuel 像这样描述机器学习：“在没有通过明确编程的情况下让电脑具有学会学习的能力”

Tom Mitchell provides a more modern definition: "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."
而Tom Mitchell提供了一个更加现代化的定义:
"如果一个电脑在执行任务T上的性能指标由性能度量P来衡量，并且能随着经验E的提升而提升，
那么我们说这个电脑程序能从经验E中学习并完成指定的任务T,且性能由P度量"

Example: playing checkers.
例如下西洋棋，其中

E = the experience of playing many games of checkers
E = 玩很多盘西洋棋的经验

T = the task of playing checkers.
T = 玩西洋棋的任务

P = the probability that the program will win the next game.
P = 程序赢得下一场游戏的概率

In general, any machine learning problem can be assigned to one of two broad classifications:
通常，许多机器学习问题能被广泛的分类为：

Supervised learning and Unsupervised learning.
监督学习和无监督学习