---

gnn_weight Connectionist Tools.
[gnn_weight : Affine / Linear Transform]

---

Detailed Description

This set of functions provide the needed funcionality for manipulating a gnn_weight : Affine / Linear Transform node from a Connectionist's point of view. That is, the gnn_weight : Affine / Linear Transform node is viewed as device that maps the inputs to outputs via connections of different strength.

The functions in this section allow to establish individual connections from a source to a destiny . The biases are special connections whose sources are constant and equal to 1.

Functions
int	gnn_weight_connect (gnn_node *node, size_t i, size_t j, double strength)
	Connect an input with an output.
int	gnn_weight_disconnect (gnn_node *node, size_t i, size_t j)
	Disconnect an input with an output.
int	gnn_weight_connect_all (gnn_node *node, double strength)
	Creates a full connection.
int	gnn_weight_disconnect_all (gnn_node *node)
	Disconnect all connections.
int	gnn_weight_connect_input (gnn_node *node, size_t i, double strength)
	Connects the i-th input to all outputs with given strength.
int	gnn_weight_disconnect_input (gnn_node *node, size_t i)
	Disconnect the i-th input from all outputs.
int	gnn_weight_freeze_connection (gnn_node *node, size_t i, size_t j)
	Freeze a connection.
int	gnn_weight_unfreeze_connection (gnn_node *node, size_t i, size_t j)
	Unfreeze a connection.
int	gnn_weight_freeze_all_connections (gnn_node *node)
	Freeze all connections.
int	gnn_weight_unfreeze_all_connections (gnn_node *node)
	Unfreeze all connections.
int	gnn_weight_connect_bias (gnn_node *node, size_t j, double strength)
	Connects a bias.
int	gnn_weight_disconnect_bias (gnn_node *node, size_t j)
	Disconnects a bias.
int	gnn_weight_connect_all_bias (gnn_node *node, double strength)
	Connects all biases.
int	gnn_weight_disconnect_all_bias (gnn_node *node)
	Disconnects all biases.
int	gnn_weight_freeze_bias (gnn_node *node, size_t j)
	Freeze a bias.
int	gnn_weight_unfreeze_bias (gnn_node *node, size_t j)
	Unfreeze a bias.
int	gnn_weight_freeze_all_biases (gnn_node *node)
	Freeze all biases.
int	gnn_weight_unfreeze_all_biases (gnn_node *node)
	Unfreeze all biases.

---

Function Documentation

int gnn_weight_connect (  gnn_node *    node, size_t    i, size_t    j, double    strength )

Connects the i-th input to the j-th output with the given strength and unfreezes it. Parameters: node  A gnn_weight : Affine / Linear Transform node. i  The index of the input. j  The index of the output. strength  The strength of the connection. Returns: Returns 0 if suceeded. Definition at line 594 of file gnn_weight.c.

int gnn_weight_connect_all (  gnn_node *    node, double    strength )

Connects the all input to the outputs with the given strength. The connections will be unfrozen. Parameters: node  A gnn_weight : Affine / Linear Transform node. strength  The strength of the connection. Returns: Returns 0 if suceeded. Definition at line 655 of file gnn_weight.c.

int gnn_weight_connect_all_bias (  gnn_node *    node, double    strength )

Connects all biases with the given strength. All its values will be unfrozen. Parameters: node  A gnn_weight : Affine / Linear Transform node. strength  The strength of the connection. Returns: Returns 0 if suceeded. Definition at line 967 of file gnn_weight.c.

int gnn_weight_connect_bias (  gnn_node *    node, size_t    j, double    strength )

Connects the bias associated with the j-th output with the given strength. The value will be unfrozen. Parameters: node  A gnn_weight : Affine / Linear Transform node. j  The index of the output associated to the bias. strength  The strength of the connection. Returns: Returns 0 if suceeded. Definition at line 907 of file gnn_weight.c.

int gnn_weight_connect_input (  gnn_node *    node, size_t    i, double    strength )

Connects the input at index i to all outputs with the given strengh strength. The connections will be unfrozen. Parameters: node  A gnn_weight : Affine / Linear Transform node. i  The input's index. strength  The strength of the connections. Returns: Returns 0 if suceeded. Definition at line 714 of file gnn_weight.c.

int gnn_weight_disconnect (  gnn_node *    node, size_t    i, size_t    j )

Disconnects the i-th input to the j-th output. The weight will be frozen to 0. Parameters: node  A gnn_weight : Affine / Linear Transform node. i  The index of the input. j  The index of the output. Returns: Returns 0 if suceeded. Definition at line 625 of file gnn_weight.c.

int gnn_weight_disconnect_all (  gnn_node *    node )

Disconnects all connections. The weights will be frozen to 0. Parameters: node  A gnn_weight : Affine / Linear Transform node. Returns: Returns 0 if suceeded. Definition at line 683 of file gnn_weight.c.

int gnn_weight_disconnect_all_bias (  gnn_node *    node )

Disconnects all biases. All its values will be frozen to 0. Parameters: node  A gnn_weight : Affine / Linear Transform node. Returns: Returns 0 if suceeded. Definition at line 995 of file gnn_weight.c.

int gnn_weight_disconnect_bias (  gnn_node *    node, size_t    j )

Disconnects the bias associated with the j-th output. The value will be frozen to 0. Parameters: node  A gnn_weight : Affine / Linear Transform node. j  The index of the output associated to the bias. Returns: Returns 0 if suceeded. Definition at line 937 of file gnn_weight.c.

int gnn_weight_disconnect_input (  gnn_node *    node, size_t    i )

Disconnects the i-th input from all outputs. The weights will be frozen to 0. Parameters: node  A gnn_weight : Affine / Linear Transform node. i  The input's index. Returns: Returns 0 if suceeded. Definition at line 755 of file gnn_weight.c.

int gnn_weight_freeze_all_biases (  gnn_node *    node )

Freezes all biases. Parameters: node  A gnn_weight : Affine / Linear Transform node. Returns: Returns 0 if suceeded. Definition at line 1077 of file gnn_weight.c.

int gnn_weight_freeze_all_connections (  gnn_node *    node )

Freezes all the connections. Parameters: node  A gnn_weight : Affine / Linear Transform node. Returns: Returns 0 if suceeded. Definition at line 852 of file gnn_weight.c.

int gnn_weight_freeze_bias (  gnn_node *    node, size_t    j )

Freezes the bias associated to the j-th output. Parameters: node  A gnn_weight : Affine / Linear Transform node. j  The index of the output. Returns: Returns 0 if suceeded. Definition at line 1024 of file gnn_weight.c.

int gnn_weight_freeze_connection (  gnn_node *    node, size_t    i, size_t    j )

Freezes the connection from the i-th input to he j-th output. Parameters: node  A gnn_weight : Affine / Linear Transform node. i  The index of the input. j  The index of the output. Returns: Returns 0 if suceeded. Definition at line 797 of file gnn_weight.c.

int gnn_weight_unfreeze_all_biases (  gnn_node *    node )

Unfreezes all biases. Parameters: node  A gnn_weight : Affine / Linear Transform node. Returns: Returns 0 if suceeded. Definition at line 1103 of file gnn_weight.c.

int gnn_weight_unfreeze_all_connections (  gnn_node *    node )

Unfreezes all the connections. Parameters: node  A gnn_weight : Affine / Linear Transform node. Returns: Returns 0 if suceeded. Definition at line 878 of file gnn_weight.c.

int gnn_weight_unfreeze_bias (  gnn_node *    node, size_t    j )

Unfreezes the bias associated to the j-th output. Parameters: node  A gnn_weight : Affine / Linear Transform node. j  The index of the output. Returns: Returns 0 if suceeded. Definition at line 1051 of file gnn_weight.c.

int gnn_weight_unfreeze_connection (  gnn_node *    node, size_t    i, size_t    j )

Unfreezes the connection going from the i-th input to the j-th output. Parameters: node  A gnn_weight : Affine / Linear Transform node. i  The index of the input. j  The index of the output. Returns: Returns 0 if suceeded. Definition at line 826 of file gnn_weight.c.

---