机器学习基石-03-2-learning with different Data Labels
来源:互联网 发布:怎么恢复网络默认设置 编辑:程序博客网 时间:2024/05/21 06:37
1.supervised learning监督学习:每一个xn都有对应的yn
2.unsupervised learning无监督学习,没有yn
3.Semi-supervised半监督学习: Coin Recognition with Someyn
4.Reinforcement Learning强化学习
当你很难定义yn="坐下"的时候,可以找另一个yn="撒尿是不对的行为”进行惩罚punish;
此时狗狗听指令坐下了,但是yn="坐下"还是很难定义,再找一个新的yn="坐下是好的行为"进行奖励reward。
reinforcement learning:
1.不是在原有的输出yn=“sit”做评价,而是在新的yn上面进行“punish惩罚”或者“reward奖励”;
2.不是大批量输入的而是sequentially一次一次地逐次输入的。
总结
阅读全文
0 0
- 机器学习基石-03-2-learning with different Data Labels
- 机器学习基石 3-2 Learning with different data label
- 机器学习基石 3.2 Learning with Different Data Label
- 机器学习基石-03-1-learning with different Output Space
- 机器学习基石-03-3-learning with different Protocol
- 机器学习基石-03-4-learning with different Input Space
- 机器学习基石 3-1 Learning with different output space
- 机器学习基石 3-3 Learning with different protocol
- 机器学习基石 3-4 Learning with different input space
- 机器学习基石 3.1 Learning with Different Output Space
- 机器学习基石 3.3 Learning with Different Protocol
- 机器学习基石 3.4 Learning with Different Input Space
- Lecture3-1Learning with different data label
- 计算机--机器学习---机器learning基石sum
- 机器学习基石2-2 PLA(Perceptron Learning Algorithm)
- 机器学习基石-2-Learning to Answer Yes/No
- (机器学习基石)Machine Learning Foundations:Lecture 2
- 机器学习基石-1-The Learning Problem
- 嵌入式学习之路
- A. Trip For Meal
- 基于动态数组的队列实现
- kd_tree搜索最近邻点
- VM安装Linux(CentOS6.5)及JDK+Tomcat+ MySQL-5.7
- 机器学习基石-03-2-learning with different Data Labels
- 《DOS命令一日通》连载说明
- 求第n个素数
- Oracle ORA-01157: 无法标识/锁定数据文件 解决方法
- 300. Longest Increasing Subsequence
- Android 开发大牛博客
- [贪心] cf883K Road Widening
- 回文问题
- 面试/笔试第三弹 —— 数据库面试问题集锦