---

gnn_divergence : Input Divergence.
[Atomic Nodes.]

---

Detailed Description

This node type implements the function given by:

In other words, it replicates the input several times on the output vector. If the output vector's size isn't a multiple of the input vector's size, that is, if can't be written as , then only the first inputs will be copied, e.g. if and is of size then

Schematically, this idea can be depicted as

The function's gradient is:

Typedefs
typedef _gnn_convergence	gnn_convergence
	The structure for a gnn_divergence : Input Divergence. node.
typedef _gnn_divergence	gnn_divergence
	The structure for a gnn_divergence : Input Divergence. node.
Functions
int	gnn_divergence_f (gnn_node *node, const gsl_vector *x, const gsl_vector *w, gsl_vector *y)
	Computes the output.
int	gnn_divergence_dx (gnn_node *node, const gsl_vector *x, const gsl_vector *w, const gsl_vector *dy, gsl_vector *dx)
	Computes .
int	gnn_divergence_dw (gnn_node *node, const gsl_vector *x, const gsl_vector *w, const gsl_vector *dy, gsl_vector *dw)
	Computes .
gnn_node *	gnn_divergence_new (size_t input_size, size_t output_size)
	Creates an input divergence node.

---

Typedef Documentation

typedef struct _gnn_convergence gnn_convergence

This datatype holds the information for a gnn_divergence : Input Divergence. node. Basically, it extends the gnn_node with special pointers to get fast accesses to the needed vector slices. Definition at line 48 of file gnn_convergence.h.

typedef struct _gnn_divergence gnn_divergence

This datatype holds the information for a gnn_divergence : Input Divergence. node. Basically, it extends the gnn_node with special pointers to get fast accesses to the needed vector slices. Definition at line 48 of file gnn_divergence.h.

---

Function Documentation

int gnn_divergence_dw (  gnn_node *    node, const gsl_vector *    x, const gsl_vector *    w, const gsl_vector *    dy, gsl_vector *    dw )  [static]

Parameters: node  A pointer to the gnn_divergence : Input Divergence. node. x  The input vector . w  The parameter vector . dy  The vector . dx  The output buffer vector . Returns: Returns 0 on success. Definition at line 191 of file gnn_divergence.c.

int gnn_divergence_dx (  gnn_node *    node, const gsl_vector *    x, const gsl_vector *    w, const gsl_vector *    dy, gsl_vector *    dx )  [static]

Parameters: node  A pointer to the gnn_divergence : Input Divergence. node. x  The input vector . w  The parameter vector . dy  The vector . dx  The output buffer vector . Returns: Returns 0 on success. Definition at line 145 of file gnn_divergence.c.

int gnn_divergence_f (  gnn_node *    node, const gsl_vector *    x, const gsl_vector *    w, gsl_vector *    y )  [static]

Parameters: node  A pointer to the gnn_divergence : Input Divergence. node. x  The input vector . w  The parameter vector . y  The output buffer vector . Returns: Returns 0 on success. Definition at line 102 of file gnn_divergence.c.

gnn_node* gnn_divergence_new (  size_t    input_size, size_t    output_size )

This function creates a node of the gnn_divergence : Input Divergence. type. Parameters: input_size  The input size . output_size  The output size . Returns: A pointer to a new gnn_divergence : Input Divergence. node. Definition at line 217 of file gnn_divergence.c.

---