Title:
|
Feature selection with iterative feature wighing methods
|
Author:
|
Rodoreda Valeri, Pol
|
Other authors:
|
Belanche Muñoz, Luis Antonio; Larrosa Bondia, Francisco Javier |
Abstract:
|
This work presents new algorithms for feature selection. The main propose is introduce the Relief algorithm to obtain an importance classification of the attributes to find which are less important. By removing the worst, an inducer will give us the performance to choose the best subset of data. |
Subject(s):
|
-Àrees temàtiques de la UPC::Informàtica -Machine learning -Algorithms -relief -selecció de variables -relief -feature selection -Aprenentatge automàtic -Algorismes |
Rights:
|
|
Document type:
|
Research/Master Thesis |
Published by:
|
Universitat Politècnica de Catalunya
|
Share:
|
|