org.encog.ml

Interface CalculateScore

All Known Implementing Classes:

EmptyScoreFunction, MultiObjectiveFitness, StochasticTrainingSetScore, TrainingSetScore, ZeroEvalScoreFunction

public interface CalculateScore

Used by simulated annealing and genetic algorithms to calculate the score for a machine learning method. This allows networks to be ranked. We may be seeking a high or a low score, depending on the value the shouldMinimize method returns.

Method Summary

Modifier and Type	Method and Description
double	calculateScore(MLMethod method) Calculate this network's score.
boolean	requireSingleThreaded()
boolean	shouldMinimize()

Method Detail

calculateScore

double calculateScore(MLMethod method)

Calculate this network's score.

Parameters:

method - The ML method.

Returns:

The score.

shouldMinimize

boolean shouldMinimize()

Returns:

True if the goal is to minimize the score.

requireSingleThreaded

boolean requireSingleThreaded()

Returns:

True, if this score function cannot be done in parallel.