model
Class SECorrelationFunction

java.lang.Object
  model.BasicCorrelationFunction
      model.DifferentiableCorrelationFunction
          model.SECorrelationFunction

All Implemented Interfaces:

VariableInputDimension

Direct Known Subclasses:

ExponentialCorrelationFunction

public class SECorrelationFunction
extends DifferentiableCorrelationFunction

Squared exponential correlation function.

corr(x1,x2) = exp(-sum_i [(x1_i - x2_i)/(tau_i)]^2). Add quick method for BasicCorrelationFunction.apply(cern.colt.matrix.DoubleMatrix2D, cern.colt.matrix.DoubleMatrix2D).

Author:

dgorur

Nested Class Summary

Nested classes/interfaces inherited from class model.BasicCorrelationFunction

BasicCorrelationFunction.TYPE

Field Summary

Fields inherited from class model.DifferentiableCorrelationFunction

gradient

Fields inherited from class model.BasicCorrelationFunction

tauVec

Constructor Summary

SECorrelationFunction()

Method Summary

double	apply(cern.colt.matrix.DoubleMatrix1D x1, cern.colt.matrix.DoubleMatrix1D x2) Computes the correlation between the outputs at x1 and x2.
cern.colt.matrix.DoubleMatrix2D	apply(cern.colt.matrix.DoubleMatrix2D x1, cern.colt.matrix.DoubleMatrix2D x2, cern.colt.matrix.DoubleMatrix2D ans) Same as BasicCorrelationFunction.apply(DoubleMatrix2D, DoubleMatrix2D), but stores the result in the supplied matrix.
void	gradient(cern.colt.matrix.DoubleMatrix1D x1, cern.colt.matrix.DoubleMatrix1D x2, double[] g) The same as DifferentiableCorrelationFunction.gradient(DoubleMatrix1D, DoubleMatrix1D), but places the result in the supplied array.

Methods inherited from class model.DifferentiableCorrelationFunction

getInstance, gradient, gradient, gradient, gradient, setInputDimension

Methods inherited from class model.BasicCorrelationFunction

apply, apply, apply, getInputDimension, getInstance, getTau, setTau

Methods inherited from class java.lang.Object

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

Constructor Detail

SECorrelationFunction

public SECorrelationFunction()

Method Detail

apply

public double apply(cern.colt.matrix.DoubleMatrix1D x1,
                    cern.colt.matrix.DoubleMatrix1D x2)

Description copied from class: BasicCorrelationFunction

Computes the correlation between the outputs at x1 and x2.

Specified by:

apply in class BasicCorrelationFunction

Parameters:

x1 - an input location.

x2 - another input location.

Returns:

the correlation between outputs at these two locations.

apply

public cern.colt.matrix.DoubleMatrix2D apply(cern.colt.matrix.DoubleMatrix2D x1,
                                             cern.colt.matrix.DoubleMatrix2D x2,
                                             cern.colt.matrix.DoubleMatrix2D ans)

Description copied from class: BasicCorrelationFunction

Same as BasicCorrelationFunction.apply(DoubleMatrix2D, DoubleMatrix2D), but stores the result in the supplied matrix.

Overrides:

apply in class BasicCorrelationFunction

Parameters:

x1 - a set of input locations.

x2 - another set of input locations.

ans - matrix to hold the result.

Returns:

ans for convenience.

gradient

public void gradient(cern.colt.matrix.DoubleMatrix1D x1,
                     cern.colt.matrix.DoubleMatrix1D x2,
                     double[] g)

Description copied from class: DifferentiableCorrelationFunction

The same as DifferentiableCorrelationFunction.gradient(DoubleMatrix1D, DoubleMatrix1D), but places the result in the supplied array.

Specified by:

gradient in class DifferentiableCorrelationFunction

Parameters:

x1 - the first point.

x2 - the second point.

g - array to hold the result.