机器学习基石-03-3-learning with different Protocol
来源:互联网 发布:淘宝服装产品描述 编辑:程序博客网 时间:2024/05/17 22:48
1.batch learning
batch of (email,spam)------>spam filter
batch of (patient,cancer)-------->cancer filter
batch of patient data-------->group of patients
batch learning:a very common protocol.
batch spam filter:predict with fixed g(固定的g)
2.online learning---which sequentially.
online learning不是固定的g(t)
PLA很容易就应用在online protocol;
reinforcement learning is often done online.因为强化学习也是sequentially。
online:hypothesis “improves” through receiving data instances sequentially.会不断地对g(t)进行修正
3.Active learning ----"learning by asking"
protocol等价于learning philosophy(学习哲学)
主动学习和之前的区别就在于,它会再回到前面的目标函数f上去“问”选定的xn对应的yn。
Active:improve hypothesis with fewer labels (hopefully) by asking questions.
多应用在labels标记很昂贵的情况下,比如珍贵药物标记。
总结:
- 机器学习基石-03-3-learning with different Protocol
- 机器学习基石 3-3 Learning with different protocol
- 机器学习基石 3.3 Learning with Different Protocol
- 机器学习基石-03-1-learning with different Output Space
- 机器学习基石-03-2-learning with different Data Labels
- 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 3-2 Learning with different data label
- 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 3.2 Learning with Different Data Label
- 机器学习基石 3.4 Learning with Different Input Space
- 机器学习基石-3-Types of Learning
- 计算机--机器学习---机器learning基石sum
- 机器学习基石笔记 Lecture 3 - Types of Learning
- 机器学习基石-04-3-Connection to Learning
- 机器学习基石-1-The Learning Problem
- 机器学习基石 4.1 Learning is Impossible?
- 数据结构:求两个多项式的相加运算
- Phaser类实现并发多阶段同步
- 1303: 因子个数
- C&C++函数内部跳转
- compareTo()方法的使用
- 机器学习基石-03-3-learning with different Protocol
- LDA与PCA都是常用的降维方法,二者的区别
- 浅谈Deep Link
- 文章标题
- JSON和JSONP区别(跨域)
- NOIP集训Week 6总结
- ArrayList和Vector和LinkedList的区别
- 编程作业50页6题 编写程序 输出满足1+2+3...+n<8888的最大正整数n
- 几种常见的优先级顺序