zoukankan      html  css  js  c++  java
  • Boosting AdaBoosting Algorithm

    http://math.mit.edu/~rothvoss/18.304.3PM/Presentations/1-Eric-Boosting304FinalRpdf.pdf

    Consider MIT Admissions

     

     【qualitative quantitative】

    2-class system (Admit/Deny)
    Both Quantitative Data and Qualitative Data
    We consider (Y/N) answers to be Quantitative (-1,+1)
    Region, for instance, is qualitative.
     
     
     
    Rules of Thumb, Weak Classifiers
    Easy to come up with rules of thumb that correctly classify the training data at
    better than chance.
    E.g. IF “GoodAtMath”==Y THEN predict “Admit”.
    Difficult to find a single, highly accurate prediction rule. This is where our Weak
    Learning Algorithm,AdaBoost, helps us.
     
     
     
    What is a Weak Learner? 
    【generalization error better than random guessing】
    For any distribution, with high probability, given polynomially many examples and polynomial time we can find a classifier with generalization error
    better than random guessing.
     
     
     
    Weak Learning Assumption
     
    We assume that our Weak Learning Algorithm (Weak
    Learner) can consistently find weak classifiers (rules of
    thumb which classify the data correctly at better than 50%)
     
    【boosting】
     
    Given this assumption, we can use boosting to generate a
    single weighted classifier which correctly classifies our
    training data at 99%-100%.
     
     
     
    【AdaBoost Specifics 】
    How does AdaBoost weight training examples optimally?
    Focus on difficult data points. The data points that have been
    misclassified most by the previous weak classifier.
    How does AdaBoost combine these weak classifiers into a
    comprehensive prediction?
    Use an optimally weighted majority vote of weak classifier.
     
     
     
    AdaBoost Technical Description
     
     
    Missing details: How to generate distribution? How to get single classifier?
     
     
    Constructing Dt
     
     
     
     
    Getting a Single Classifier

     
     
  • 相关阅读:
    Android-IntentFilter
    Activity-Flag标志位
    设计模式杂谈
    Android-语言国际化
    Android 常见SD卡操作
    Android
    nginx,wsgi,django的关系
    mac安装python-mysql
    mac mysql命令行
    地址空间 32位和64位
  • 原文地址:https://www.cnblogs.com/rsapaper/p/7768681.html
Copyright © 2011-2022 走看看