ForwardBackwardGradientTGradient Method (Double, T, Int32)

Computes the gradient (vector of derivatives) vector for the cost function, which may be used to guide optimization.

Namespace: Accord.Statistics.Models.Fields.Learning
Assembly: Accord.Statistics (in Accord.Statistics.dll) Version: 3.8.0

Syntax

public double[] Gradient(
	double[] parameters,
	T[][] inputs,
	int[] outputs
)

Public Function Gradient ( 
	parameters As Double(),
	inputs As T()(),
	outputs As Integer()
) As Double()

parameters: Type: SystemDouble
The parameter vector lambda to use in the model.
inputs: Type: T
The inputs to compute the cost function.
outputs: Type: SystemInt32
The respective outputs to compute the cost function.

Type: Double
The value of the gradient vector for the given parameters.