NAME

compute_svm - Builds a Support Vector Machine

SYNOPSIS

#include "wrap_svm/wrap_svm.h"

Example compile flags (system dependent):
  -DLINUX_X86_64 -DLINUX_X86_64_OPTERON  -DGNU_COMPILER 
   -I/home/kobus/include
   -L/home/kobus/misc/load/linux_x86_64_opteron -L/usr/lib/x86_64-linux-gnu
  -lKJB                               -lfftw3  -lgsl -lgslcblas -ljpeg  -lSVM -lstdc++                    -lpthread -lSLATEC -lg2c    -lacml -lacml_mv -lblas -lg2c      -lncursesw 


int compute_svm
(
	const char *training_file_name,
	const char *model_file_name,
	const char *scale_path
);

DESCRIPTION

This routine builds a Support Vector Machine using one of possibly several wrapped methods under the control of user supplied options. The default is to use libsvm if it is available. This KJB library interface to support vector machine code is file based. It is up to the user to be consistent regarding building and predicting as this is not currently validated.

RETURNS

NO_ERROR on success, and ERROR on failure, with an error message being set. This routine will fail if the routine used build the SVM fails.

DISCLAIMER

This software is not adequatedly tested. It is recomended that results are checked independantly where appropriate.

AUTHOR

Ranjini Swaminathan and Kobus Barnard

DOCUMENTER

Ranjini Swaminathan and Kobus Barnard

SEE ALSO

predict_with_svm