MultiClassification.PredictedClass Method

MultiClassificationPredictedClass Method

Calculates the classification probablities for the input pattern x, and returns the class with the highest probability.

Namespace: Imsl.DataMining.Neural
Assembly: ImslCS (in ImslCS.dll) Version: 6.5.2.0

Syntax

public virtual int PredictedClass(
	double[] x
)

Public Overridable Function PredictedClass ( 
	x As Double()
) As Integer

public:
virtual int PredictedClass(
	array<double>^ x
)

abstract PredictedClass : 
        x : float[] -> int 
override PredictedClass : 
        x : float[] -> int

Parameters

x: Type: SystemDouble
The double array containing the network input patterns to classify. The length of x should equal the number of inputs in the network.

Return Value

Type: Int32
The classification predicted by the trained network for x. This will be one of the integers 1,2,...,nClasses, where nClasses is equal to nOuptuts. nOuptuts is the number of outputs in the network representing the number of classes.

Remarks

This method classifies patterns into one of the target classes based upon the patterns values.

Reference

MultiClassification Class

Imsl.DataMining.Neural Namespace