Preprocessor PCACut performs principial component analysis on the input vectors and keeps only the n eigenvectors with eigenvalues above a certain threshold.
On preprocessing the stored covariance matrix is used to project vectors into eigenspace only returning vectors of reduced dimension n. Optional whitening is performed.
This is only useful if the dimensionality of the data is rather low, as the covariance matrix is of size num_feat*num_feat. Note that vectors don't have to have zero mean as it is substracted.
Definition at line 48 of file PCA.h.
List of all members.
Constructor & Destructor Documentation
|do_whitening ||do whitening |
|mode ||mode of pca |
|thresh ||threshold |
Definition at line 27 of file PCA.cpp.
Definition at line 57 of file PCA.cpp.
Member Function Documentation
get eigenvalues of PCA
Definition at line 253 of file PCA.cpp.
get mean vector of original data
Definition at line 258 of file PCA.cpp.
|virtual const char* get_name
get transformation matrix, i.e. eigenvectors (potentially scaled if do_whitening is true)
Definition at line 248 of file PCA.cpp.
Member Data Documentation
Definition at line 116 of file PCA.h.
Definition at line 118 of file PCA.h.
Definition at line 114 of file PCA.h.
Definition at line 122 of file PCA.h.
Definition at line 108 of file PCA.h.
Definition at line 120 of file PCA.h.
Definition at line 110 of file PCA.h.
num old dim
Definition at line 112 of file PCA.h.
Definition at line 124 of file PCA.h.
The documentation for this class was generated from the following files: