机器学习定义

卡耐基梅隆大学的 Tom Michael Mitchell 教授在 Machine Learning 一书中对机器学习进行了明确定义：

---

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.

---

中文译文：

如果一个计算机程序可以在任务 T 上，随着经验 E 的增加，效果 P 也随之增加，则称该程序从经验 E 中学习。