get_prep_info_class_svm🔗
Short description🔗
get_prep_info_class_svm — Compute the information content of the preprocessed feature vectors
of a support vector machine
Signature🔗
get_prep_info_class_svm( class_svm SVMHandle, string Preprocessing, out real InformationCont, out real CumInformationCont )
Description🔗
get_prep_info_class_svm computes the information content of
the training vectors that have been transformed with the
preprocessing given by Preprocessing.
Preprocessing can be set to 'principal_components'
or 'canonical_variates'. The preprocessing methods are
described with create_class_svm. The information content is
derived from the variations of the transformed components of the
feature vector, i.e., it is computed solely based on the training
data, independent of any error rate on the training data. The
information content is computed for all relevant components of the
transformed feature vectors (NumFeatures for
'principal_components' and min(NumClasses - 1,
NumFeatures) for 'canonical_variates', see
create_class_svm), and is returned in
InformationCont as a number between 0 and 1. To convert
the information content into a percentage, it simply needs to be
multiplied by 100. The cumulative information content of the first
\(n\) components is returned in the \(n\)-th component of
CumInformationCont, i.e., CumInformationCont
contains the sums of the first \(n\) elements of
InformationCont. To use get_prep_info_class_svm, a
sufficient number of samples must be added to the support vector
machine (SVM) given by SVMHandle by using
add_sample_class_svm or read_samples_class_svm.
InformationCont and CumInformationCont can be used
to decide how many components of the transformed feature vectors
contain relevant information. An often used criterion is to require
that the transformed data must represent x% (e.g., 90%) of the
data. This can be decided easily from the first value of
CumInformationCont that lies above x%. The number thus
obtained can be used as the value for NumComponents in a
new call to create_class_svm. The call to
get_prep_info_class_svm already requires the creation of an
SVM, and hence the setting of NumComponents in
create_class_svm to an initial value. However, when
get_prep_info_class_svm is called, it is typically not known
how many components are relevant, and hence how to set
NumComponents in this call. Therefore, the following
two-step approach should typically be used to select
NumComponents: In a first step, an SVM with the maximum
number for NumComponents is created (NumFeatures
for 'principal_components' and min(NumClasses -
1, NumFeatures) for 'canonical_variates'). Then,
the training samples are added to the SVM and are saved in a file
using write_samples_class_svm. Subsequently,
get_prep_info_class_svm is used to determine the information
content of the components, and with this NumComponents.
After this, a new SVM with the desired number of components is
created, and the training samples are read with
read_samples_class_svm. Finally, the SVM is trained with
train_class_svm.
Execution information🔗
Execution information
-
Multithreading type: reentrant (runs in parallel with non-exclusive operators).
-
Multithreading scope: global (may be called from any thread).
-
Processed without parallelization.
Parameters🔗
SVMHandle (input_control) class_svm → (handle)
SVM handle.
Preprocessing (input_control) string → (string)
Type of preprocessing used to transform the feature vectors.
Default: 'principal_components'
List of values: 'canonical_variates', 'principal_components'
InformationCont (output_control) real-array → (real)
Relative information content of the transformed feature vectors.
CumInformationCont (output_control) real-array → (real)
Cumulative information content of the transformed feature vectors.
Example🔗
(HDevelop)
* Create the initial SVM
create_class_svm (NumFeatures, 'rbf', 0.01, 0.01, NumClasses,\
'one-versus-all', 'normalization', NumFeatures,\
SVMHandle)
* Generate and add the training data
for J := 0 to NumData-1 by 1
* Generate training features and classes
* Data = [...]
* Class = ...
add_sample_class_svm (SVMHandle, Data, Class)
endfor
write_samples_class_svm (SVMHandle, 'samples.mtf')
* Compute the information content of the transformed features
get_prep_info_class_svm (SVMHandle, 'principal_components',\
InformationCont, CumInformationCont)
* Determine NumComp by inspecting InformationCont and CumInformationCont
* NumComp = [...]
* Create the actual SVM
create_class_svm (NumFeatures, 'rbf', 0.01, 0.01, NumClasses, \
'one-versus-all', 'principal_components', \
NumComp, SVMHandle)
* Train the SVM
read_samples_class_svm (SVMHandle, 'samples.mtf')
train_class_svm (SVMHandle, 0.001, 'default')
write_class_svm (SVMHandle, 'classifier.svm')
Result🔗
If the parameters are valid the operator
get_prep_info_class_svm returns the value 2 (H_MSG_TRUE). If
necessary, an exception is raised.
get_prep_info_class_svm may return the error 9211 (Matrix is
not positive definite) if Preprocessing \(=\)
'canonical_variates' is used. This typically indicates
that not enough training samples have been stored for each class.
Combinations with other operators🔗
References🔗
Christopher M. Bishop: “Neural Networks for Pattern Recognition”; Oxford University Press, Oxford; 1995.
Andrew Webb: “Statistical Pattern Recognition”; Arnold, London; 1999.
Module🔗
Foundation