where
.
This function is a member of the more general class of sigmoid functions, which have the property to "squash" its inputs to a very restricted output interval.
The Logistic Sigmoid is assymmetric and its outputs lie between
. It has been said that it leads to slower convergence in training than the Hyperbolic Tangent.
Functions | |
| int | gnn_logistic_f (gnn_node *node, const gsl_vector *x, const gsl_vector *w, gsl_vector *y) |
| Computes the output. | |
| int | gnn_logistic_dx (gnn_node *node, const gsl_vector *x, const gsl_vector *w, const gsl_vector *dy, gsl_vector *dx) |
Computes
. | |
| gnn_node * | gnn_logistic_new (int input_size, double a, double b) |
| Creates a Logistic Sigmoid activation function node. | |
| gnn_node * | gnn_logistic_standard_new (int input_size) |
| Creates a standard Logistic Sigmoid function node. | |
| double | gnn_logistic_get_a (gnn_node *node) |
Returns the amplitude constant
. | |
| void | gnn_logistic_set_a (gnn_node *node, double a) |
Sets the amplitude constant
. | |
| double | gnn_logistic_get_b (gnn_node *node) |
Gets the streching factor
. | |
| void | gnn_logistic_set_b (gnn_node *node, double b) |
Sets the streching factor
. | |
|
||||||||||||||||||||||||
|
This functions computes the gradient of the logistic sigmoid function, given dedy (
Definition at line 154 of file gnn_logistic.c. |
|
||||||||||||||||||||
|
This functions evaluates the logistic sigmoid function.
Definition at line 107 of file gnn_logistic.c. |
|
|
Definition at line 282 of file gnn_logistic.c. |
|
|
Definition at line 308 of file gnn_logistic.c. |
|
||||||||||||||||
|
This function creates a node of the gnn_logistic type. This node computes
where
Definition at line 211 of file gnn_logistic.c. |
|
||||||||||||
|
Definition at line 295 of file gnn_logistic.c. |
|
||||||||||||
|
Definition at line 321 of file gnn_logistic.c. |
|
|
This function creates a node of the gnn_logistic type:
where
Definition at line 269 of file gnn_logistic.c. |
1.2.18