JMSLTM Numerical Library 4.0

com.imsl.datamining.neural
Interface QuasiNewtonTrainer.Error

All Superinterfaces:
Serializable
Enclosing interface:
QuasiNewtonTrainer

public static interface QuasiNewtonTrainer.Error
extends Serializable

Error function to be minimized by trainer. This trainer attempts to solve the problem

min_{w} sum_{i=0}^{n-1} e(y_i, hat{y}_i)

where w are the weights, n is the number of training patterns, y_i is a training target output and hat{y}_i is its forecast value.

This interface defines the function e(y, hat{y}) and its derivative with respect to its computed value, de/dhat{y}.


Method Summary
 double error(double[] computed, double[] expected)
          Returns the contribution to the error from a single training output target.
 double[] errorGradient(double[] computed, double[] expected)
          Returns the derivative of the error function with respect to the forecast output.
 

Method Detail

error

public double error(double[] computed,
                    double[] expected)
Returns the contribution to the error from a single training output target. This is the function e(y_i, hat{y}_i).

Parameters:
computed - A double representing the computed value.
expected - A double representing the expected value.
Returns:
A double representing the contribution to the error from a single training output target.

errorGradient

public double[] errorGradient(double[] computed,
                              double[] expected)
Returns the derivative of the error function with respect to the forecast output.

Parameters:
computed - A double representing the computed value.
expected - A double representing the expected value.
Returns:
A double representing the derivative of the error function with respect to the forecast output.

JMSLTM Numerical Library 4.0

Copyright 1970-2006 Visual Numerics, Inc.
Built June 1 2006.