PRTools Contents

PRTools User Guide

featself

FEATSELF

Trainable mapping for forward feature selection

    [W,R] = FEATSELF(A,CRIT,K,T)
    [W,R] = A*FEATSELF([],CRIT,K,T)
    [W,R] = A*FEATSELF(CRIT,K,T)
    [W,R] = FEATSELF(A,CRIT,K,N)
    [W,R] = A*FEATSELF([],CRIT,K,N)
    [W,R] = A*FEATSELF(CRIT,K,N)

Input
 A Training dataset
 CRIT Name of the criterion or untrained mapping  (default: 'NN', i.e. the LOO 1-Nearest Neighbor error)
 K Number of features to select (default: K = 0, return optimal set)
 T Tuning dataset (optional)
 N Number of cross-validation folds (optional)

Output
 W Output feature selection mapping
 R Matrix with step-by-step results

Description

Forward selection of K features using the dataset A. CRIT sets the  criterion used by the feature evaluation routine FEATEVAL. If the  dataset T is given, it is used as test set for FEATEVAL. Alternatvely a  a number of cross-validation N may be supplied. For K = 0, the optimal  feature set (corresponding to the maximum value of FEATEVAL) is returned.  The result W can be used for selecting features using B*W.  The selected features are stored in W.DATA and can be found by +W.  In R, the search is reported step by step as

     R(:,1) : number of features
     R(:,2) : criterion value
     R(:,3) : added / deleted feature

See also

mappings, datasets, feateval, featsellr, featsel, featselo, featselb, featseli, featselp, featselm,

PRTools Contents

PRTools User Guide

This file has been automatically generated. If badly readable, use the help-command in Matlab.