一、定义
Machine Learning:
“Field of study that gives computers the ability to learn without being explicitly programmed”, Arthur Samuel (1959)
“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.” Tom. E. Mitchell.
二、机器学习的分类
- 监督学习Supervised learning:对于给定数据集,所有的输入都人为的打上标签,系统通过训练来学习输入和输出的关系。
- 无监督学习Unsupervised learning:对于给定数据集,所有数据都是没有人为打上标签的,需要系统自己去寻找各个输入的相互关系。
- 半监督学习Semi-supervised learning:部分数据有标签,部分数据没有标签
- 强化学习Reinforcement learning:通过与环境交互,不断尝试出获得最大奖励的方案
三、学习过程的输出:
- 分类Classification(监督学习)
- 回归Regression(监督学习)
- 聚类Clustering(无监督)
- 降维Dimensionality reduction(无监督学习)
- 特征抽取Feature learning(监督&无监督)
- 行为Behaviour policy:输出为状态-行动对 (强化学习)