PHP Class MCordingley\Regression\Algorithm\GradientDescent\StoppingCriteria\GradientNorm

Good for Batch descent, when the gradient is fairly stable from one iteration to the next. Not so good for Stochastic descent and MiniBatch with small batch sizes, as those gradients won't settle near zero even as the weights converge.

Inheritance: implements MCordingley\Regression\Algorithm\GradientDescent\StoppingCriteria\StoppingCriteria

Afficher le fichier Open project: mcordingley/regression Class Usage Examples

Méthodes publiques

Méthode	Description
__construct ( float $eta = 6.103515625E-5, integer $pNorm = 2 )
converged ( array $gradient, array $coefficients ) : boolean

Method Details

__construct() public méthode

public __construct ( float $eta = 6.103515625E-5, integer $pNorm = 2 )
$eta	float
$pNorm	integer

converged() public méthode

public converged ( array $gradient, array $coefficients ) : boolean
$gradient	array
$coefficients	array
Résultat	boolean