PHP Class MCordingley\Regression\Algorithm\GradientDescent\Schedule\Fixed

Since the gradient of the error becomes shallower as the descent nears convergence, this will naturally shrink the updates into the error function's minimum. However, too large of a step size will lead to the descent diverging and too small of a step size will lead to an extremely long descent. Unfortunately, choosing a good step size is a matter of trial and error.
Inheritance: implements MCordingley\Regression\Algorithm\GradientDescent\Schedule\Schedule
Datei anzeigen Open project: mcordingley/regression Class Usage Examples

Public Methods

Method Description
__construct ( float $stepSize = 0.01 )
step ( integer $featureIndex ) : float
update ( array $gradient )

Method Details

__construct() public method

public __construct ( float $stepSize = 0.01 )
$stepSize float

step() public method

public step ( integer $featureIndex ) : float
$featureIndex integer
return float

update() public method

public update ( array $gradient )
$gradient array