|
PLSAOptions Class Reference |  |
Option object for the pLSA algorithm. More...
#include <vigra/unsupervised_decomposition.hxx>
Public Member Functions | |
| PLSAOptions & | maximumNumberOfIterations (unsigned int n) |
| PLSAOptions & | minimumRelativeGain (double g) |
| PLSAOptions & | normalizedComponentWeights (bool v=true) |
| PLSAOptions () | |
Detailed Description
Option object for the pLSA algorithm.
Constructor & Destructor Documentation
| PLSAOptions | ( | ) |
Initialize all options with default values.
Member Function Documentation
| PLSAOptions& maximumNumberOfIterations | ( | unsigned int | n | ) |
Maximum number of iterations which is performed by the pLSA algorithm.
default: 50
| PLSAOptions& minimumRelativeGain | ( | double | g | ) |
Minimum relative gain which is required for the algorithm to continue the iterations.
default: 1e-4
| PLSAOptions& normalizedComponentWeights | ( | bool | v = true | ) |
Normalize the entries of the zv result array.
If true, the columns of zv sum to one. Otherwise, they have the same column sum as the original feature matrix.
default: true
The documentation for this class was generated from the following file: