Lecture2-3Guarantee of PLA
2015-09-19 22:11
169 查看
Linear Separable
If PLA halts(no mistakes),(necessary condition) allows some w to make no mistakeCall linear separable
Linear Separable ⟺ exists perfect wf such that yn=sign(wTfxn)
<
24000
span class="mrow" id="MathJax-Span-7240">wf perfect hence every xn correctly away from the line:
yn(t)wTfxn(t)≥minnynwTfxn>0
Fact:wt gets closer to wf by updating.
wTfwt+1=wTf(wt+yn(t)xn(t))≥wTfwt+yn(t)wTfxn(t)≥wTfwt+minnynwTfxn>wTfwt
Fact: wt doesn’t grow too fast.
Derivation
After T derivations, we can have:Remark1
∵wTfwT∴wTfwT∥wTf∥=wTf(wT−1+yn(T)xn(T))=wTfwT−1∥wTf∥+wTfyn(T)xn(T)∥wTf∥≥wTfwT−1∥wTf∥+minnwTfynxn∥wTf∥≥wTfwT−1∥wTf∥+ρ≥wTfwT−2∥wTf∥+2ρ...≥Tρ
Remark2
∥wT∥2=∥wT−1+yn(T)xn(T)∥2=∥wT−1∥2+∥yn(T)xn(T)∥2+2wTT−1yn(T)xn(T)≤∥wT−1∥2+∥xn(T)∥2≤∥wT−1∥2+maxn∥xn∥2≤∥wT−1∥2+R2≤∥wT−2∥2+2R2...≤TR2
∴ the perceptron iterates at most T iterations before it stops, if is linear separable
∴1≥wTfwT∥wf∥∥wT∥≥TρT‾‾√R=T‾‾√ρR∴T≤R2ρ2
where ρ=minnwTfynxn∥wTf∥ and R=maxn∥xn∥.
相关文章推荐
- Leetcode65: Move Zeroes
- ARM学习记录1
- NIO——buffer
- NIO——Channel
- bzoj-2095 Bridges
- Zookeeper linux下使用
- 自己写的轻量级PHP框架trig与laravel5.1,yii2性能对比
- yii rules 验证详解
- MongoDB操作
- Windows Server 2008 R2网站访问PHP响应慢的解决方法
- 黑马程序员-----反射技术
- Mining Massive Datasets课程笔记(一)
- Java常用类及集合框架小实验
- 偏执的我从Linux到Windows的感受
- iOS 多线程及其他补充
- Guide to installing 3rd party JARs
- 旋转数组的最小数字
- 基于3520D的HDMI产品设计
- CSS Sprite的使用
- 为系统菜单添加图标--------暴力反射