关于机器学习,有两种不同的定义。Arthur Samuel把它描述为:
“the field of study that gives computers the ability to learn without being explicitly programmed.”
“在研究领域,给予机器自主学习的能力,而不依靠确定的计划。”,这是一个早期的不正式的定义。
另一个更成熟的定义,是由Tom Mitchell提出来的:
“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.”
一个计算机程序能够从经验E中学习(学习任务是T,学习的表现用P衡量),如果这个程序在任务T与表现衡量P下,可以通过经验E得到改进。
举个玩跳棋的例子:
E = 玩很多局跳棋的经验
T = 玩跳棋任务
P = 程序能赢得下一盘的可能性
实际上,大多数机器学习都可以分为两类:
Supervised learning and Unsupervised learning
监督学习和非监督学习
网友评论