Enumeration of initialization types for SOM.
More...
|
int | random = 0 |
| Weights are randomly distributed using Gaussian distribution (0, 1). More...
|
|
int | random_centroid = 1 |
| Weights are randomly distributed using Gaussian distribution (input data centroid, 1). More...
|
|
int | random_surface = 2 |
| Weights are randomly distrbiuted using Gaussian distribution (input data centroid, surface of input data). More...
|
|
int | uniform_grid = 3 |
| Weights are distributed as a uniform grid that covers whole surface of the input data. More...
|
|
Enumeration of initialization types for SOM.
- See also
- som
Definition at line 69 of file som.py.
◆ random
int pyclustering.nnet.som.type_init.random = 0 |
|
static |
Weights are randomly distributed using Gaussian distribution (0, 1).
Definition at line 78 of file som.py.
◆ random_centroid
int pyclustering.nnet.som.type_init.random_centroid = 1 |
|
static |
Weights are randomly distributed using Gaussian distribution (input data centroid, 1).
Definition at line 81 of file som.py.
◆ random_surface
int pyclustering.nnet.som.type_init.random_surface = 2 |
|
static |
Weights are randomly distrbiuted using Gaussian distribution (input data centroid, surface of input data).
Definition at line 84 of file som.py.
◆ uniform_grid
int pyclustering.nnet.som.type_init.uniform_grid = 3 |
|
static |
Weights are distributed as a uniform grid that covers whole surface of the input data.
Definition at line 87 of file som.py.
The documentation for this class was generated from the following file: