---

gnn_mse : Mean-Square-Error Criterion.
[gnn_criterion : Basic Criterion Function.]

---

Detailed Description

This datatype implements the MSE criterion, given by

Although widely used, this cost-function is not always the best suited criterion. Since the errors are squared up and summed togheter, those components with large errors can greatly influence the learning process during training. It has been shown that for a class of problems, the MSE criterion can lead to trappings in local minima, failing to find a solution although there is at least one.

Functions
double	gnn_mse_e (gnn_criterion *crit, const gsl_vector *y, const gsl_vector *t)
	The evaluation function.
int	gnn_mse_dy (gnn_criterion *crit, const gsl_vector *y, const gsl_vector *t, gsl_vector *dy)
	The gradient evaluation function.
gnn_criterion *	gnn_mse_new (size_t size)
	Creates a new gnn_mse criterion.

---

Function Documentation

int gnn_mse_dy (  gnn_criterion *    crit, const gsl_vector *    y, const gsl_vector *    t, gsl_vector *    dy )

This function implements the gnn_mse criterion's gradient evaluation function given by Parameters: crit  A pointer to a gnn_mse criterion. y  A pointer to an estimation vector . t  A pointer to the desired target vector . dy  A pointer to a buffer vector where the result should be placed. Returns: Returns 0 if succeeded. Definition at line 133 of file gnn_mse.c.

double gnn_mse_e (  gnn_criterion *    crit, const gsl_vector *    y, const gsl_vector *    t )

This function corresponds to the evaluation of the MSE criterion. Parameters: crit  A pointer to a gnn_mse criterion. y  A pointer to an estimation vector . t  A pointer to the desired target vector . Returns: A real number corresponding to the value of the criterion. Definition at line 85 of file gnn_mse.c.

gnn_criterion* gnn_mse_new (  size_t    size )

This function creates a new gnn_mse of the given size. * Parameters: size  The size of the estimation and the target vector and . Returns: Returns a pointer to a new gnn_mse or NULL if failed. Definition at line 184 of file gnn_mse.c.

---