问题1:什么是机器学习以及机器学习的通用算法
如今一般使用的是Tom Mitchell对机器学习的定义: 原文为:
A computer program is said to learn from experience E with respecet to some task T and some performance measure P,if its performance ont T, as measured by P,improves with experience E.
即:计算机程序从经验E中学习,解决某一任务T,进行某一性能度量p,通过p测定在T上的表现因经验E而提高
Machine learning algorithms:
1:supervised learning (监督学习)unsupervised learning (非监督学习)为主要的学习算法
2: 此外还有reinforcement learning (强化学习),recommender systems(推荐系统)
supervised learning:
gives a dataset in whitch the "right answer" are given .
1.regression question(回归问题) continuous valued 目的:预测一个连续值的输出
2.classification question(分类问题)Discrete valued 目的:预测离散值的输出
unsupervised learning:
gives a dataset but not told what to do with it
clustering algorithm(聚类算法):告诉数据集,将其分为不同的聚类
always used in:
1.organize computing clusters 2.social network analysis 3.market segmentation 4.Astronomicla data analysis