data_mining:gradient_boosting

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
data_mining:gradient_boosting [2016/02/01 22:12] – [Warum boosting?] phreazerdata_mining:gradient_boosting [2017/07/19 18:34] (current) – [Basic idea] phreazer
Line 49: Line 49:
 Beispiel (quadratischer Fehler):  Beispiel (quadratischer Fehler): 
 $$R = \frac{1}{n} \sum_{i=1}^n p(Y_i - f(X_i))^2$$ $$R = \frac{1}{n} \sum_{i=1}^n p(Y_i - f(X_i))^2$$
 +
 +===== Basic idea =====
 +
 +  - Generate simple regression model. 
 +  - Compute error residual.
 +  - Learn to predict residual
 +  - Add to initial model
  • data_mining/gradient_boosting.1454364725.txt.gz
  • Last modified: 2016/02/01 22:12
  • by phreazer