Version 3 (modified by gkronber, 12 years ago) (diff) |
---|

# Symbolic Regression Problem

**Problem Parameters:**

Parameter | Description |
---|---|

BestKnownQuality | The minimal error value that reached by symbolic regression solutions for the problem. |

DataAnalysisProblemData | The data set, target variable and input variables of the data analysis problem. |

Evaluator | SymbolicRegressionScaledMeanSquaredErrorEvaluator: The operator which should be used to evaluate symbolic regression solutions. |

FunctionTreeGrammar | The grammar that should be used for symbolic regression models. |

LowerEstimationLimit | The lower limit for the estimated value that can be returned by the symbolic regression model. |

MaxExpressionDepth | Maximal depth of the symbolic expression. |

MaxExpressionLength | Maximal length of the symbolic expression. |

MaxFunctionArguments | Maximal number of arguments of automatically defined functions. |

MaxFunctionDefiningBranches | Maximal number of automatically defined functions. |

Maximization | Set to false as the error of the regression model should be minimized. |

SolutionCreator | ProbabilisticTreeCreator: The operator which should be used to create new symbolic regression solutions. |

SymbolicExpressionTreeInterpreter | The interpreter that should be used to evaluate the symbolic expression tree. |

UpperEstimationLimit | The upper limit for the estimated value that can be returned by the symbolic regression model. |

**Is there a sample/tutorial?**

Sure. We have configured a standard genetic programming algorithm to solve a symbolic regression problem (Boston Housing dataset):