MultiClassification.ComputeStatistics Method

MultiClassificationComputeStatistics Method

Computes classification statistics for the supplied network patterns and their associated classifications.

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

Syntax

public virtual double[] ComputeStatistics(
	double[,] xData,
	int[] yData
)

Public Overridable Function ComputeStatistics ( 
	xData As Double(,),
	yData As Integer()
) As Double()

public:
virtual array<double>^ ComputeStatistics(
	array<double,2>^ xData, 
	array<int>^ yData
)

abstract ComputeStatistics : 
        xData : float[,] * 
        yData : int[] -> float[] 
override ComputeStatistics : 
        xData : float[,] * 
        yData : int[] -> float[]

Parameters

xData: Type: SystemDouble
A double matrix specifying the input training patterns. The number of columns in xData must equal the number of Nodes in the InputLayer.
yData: Type: SystemInt32
An int[] containing the output classification patterns. The values in yData must be in the range of one to the number of OutputPerceptrons in the network.

Return Value

Type: Double
A double[] containing the cross-entropy error and the classification error rate.

Remarks

Method ComputeStatistics returns a two element array where the first element returned is the cross-entropy error; the second is the classification error rate. The classification error rate is calculated by comparing the estimated classification probabilities to the target classifications. If the estimated probability for the target class is not the largest among the target classes, then the pattern is tallied as a classification error.

Reference

MultiClassification Class

Imsl.DataMining.Neural Namespace