## Computational Learning Theory (Cont.)

The Vapnik-Chervonenkis(VC) dimension

- Shattering a set of instances
- VC dimension

- Definition and several examples


### The Vapnik-Chervonenkis(VC) dimension

• An unbiased hypothesis spaceis one that shatters the instance space X.
• Sometimes X cannotbe shattered by H, but a large subset of it can.
• Definition: The Vapnik-ChervonenkisDimensionVC(H)of hypothesis space Hdefined over instance space X
• is the size of the largestfinite subset of X shattered by H.
• if arbitrarily large finite sets of X can be shattered by H, then VC(H)≡∞
• If we find ONE set of instances of size d that can be shattered, then VC(H) d.
• To show that VC(H)

### VC Dim. Examples (1)

• Example 1:
• Instance space X: the set of real numbers
X = R
• H is the set of intervals on the real number axis.
• Form of H is: a < x < b
• VC(H) = ?

#### 周志华《Machine Learning》学习笔记（15）--半监督学习

2017-07-04 22:16:32

#### Foundation of Machine Learning 笔记第四部分 —— Generalities 以及对不一致假设集的PAC学习证明

2017-03-07 10:40:07

#### certificate学习

2016-07-21 11:04:58

#### 自己关于学习js的一些经历

2016-11-26 11:54:06

#### 半监督学习

2018-04-18 16:53:54

#### 深度学习如何入门？

2016-05-25 17:16:41

#### 后端框架的学习流程

2017-01-01 13:43:12

#### 纯干货15 48个深度学习相关的平台和开源工具包，一定有很多你不知道的！！！

2017-08-02 19:44:52

#### PAC-learning 新理解

2015-04-23 11:03:30

#### PAC Learning Framework可能近似正确学习

2016-05-07 19:17:29

## 不良信息举报

Agnostic Learning (不可知学习)