Package com.imsl.datamining.neural

Class QuasiNewtonTrainer.Objective

java.lang.Object

com.imsl.datamining.neural.QuasiNewtonTrainer.Objective

All Implemented Interfaces:

MinUnconMultiVar.Function

Direct Known Subclasses:

QuasiNewtonTrainer.BlockObjective, QuasiNewtonTrainer.GradObjective

Enclosing class:

QuasiNewtonTrainer

protected class QuasiNewtonTrainer.Objective
extends Object
implements MinUnconMultiVar.Function

The Objective class is passed to the optimizer.

Field Summary

Fields

Modifier and Type	Field	Description
protected int	nFunctionEvaluations
protected int	nObs
protected int	nY

Method Summary

Modifier and Type	Method	Description
double	f(double[] weights)	Public interface for the multivariate function to be minimized.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Details

nObs

protected int nObs

nY

protected int nY

nFunctionEvaluations

protected int nFunctionEvaluations

Method Details

f

public double f(double[] weights)

Description copied from interface: MinUnconMultiVar.Function

Public interface for the multivariate function to be minimized.

Specified by:

f in interface MinUnconMultiVar.Function

Parameters:

weights - a double array, the point at which the function is to be evaluated

Returns:

a double, the value of the function at x