Evaluation of symbolic regression solutions based on the correlation coefficient instead of the (scaled) MSE

[gkronber]

Maximizing the Pearson's correlation coefficient r² is equivalent to maximization of the scaled MSE, however the calculation of r² is more efficient because it can be calculated in a single pass while the scaled MSE has to be calculated in two passes.

[gkronber]

Added correlation coefficient evaluator for symbolic regression problems with r4127.

[gkronber]

r4190:

• Moved upper and lower estimation limit parameters into ISymbolicRegressionEvaluator interface and introduced an Evaluate method in the interface in preparation for a ISymbolicRegressionEvaluator parameter for the validation best solution analyzer.

[gkronber]

r4191:

• Changed validation best solution analyzer and tournament pruning operator to use the evaluator specified in the problem parameters.

[swagner]

Milestone Iteration 4 deleted

[swagner]

Milestone Current deleted