[Master Index] [Index for export/lyngby]

lyngby_efir_main

(export/lyngby/lyngby_efir_main.m)


Function Synopsis

[result_efir,numcoef] = lyngby_efir_main(pn, X, R, ...

Help text

 lyngby_efir_main     - Main exhautive FIR function
 
       function [result_efir,numcoef] = lyngby_efir_main(PN, X, R,...
                       maxfilterlength, numreshuffle)

       Input:  PN                Input (the paradigm)
               X                Target (the datamatrix)
               R                 Run structure
               maxfilterlength   Filter length (lag)
               numreshuffle      Number of crossvalidation
                                 permutations

       Output: result_efir       Filter coefficients
               numcoef           Optimal number of filter
                                 coefficients

       The FIR filter used in combination the SVD pseudo
       inversion. The optimal model in each voxel is determined by
       the Generalization error, based on the exhaustive search
       through a 2D space. The 2D space is span by 'models' and
       'splitratios'. The 'splitratio' is simply how the dataset
       is split into a trainset and a testset. The 'models' is the
       size of the SVD pseudo inversion length.

       See also: lyngby_fir_main

Cross-Reference Information

This function calls
This function is called by

Produced by mat2html on Wed Jul 29 15:43:40 2009
Cross-Directory links are: OFF