Skip to Content
BayesiaLabBayesiaLab User GuideMenusAnalysisFunction OptimizationGenetic

Genetic Function Optimization

Overview

Genetic Function Optimization is a search algorithm based on a genetic algorithm that finds sets of evidence (Hard Evidence and/or Numerical Evidence) that optimize the value of a Function node. Instead of only maximizing or minimizing the function value, it is also possible to specify a target value directly.

This is the same genetic search used for Target Optimization, applied here to a Function node rather than to a Target node.

Allow No Evidence

The genetic algorithm can create solutions without instantiating all the nodes included in the optimization, that is, without setting evidence on every selected observable node.

Filter

A filter can remove solutions from the output, both from the report and from the Evidence Scenario file, based on a filtering power:

  • 0: all solutions are reported.
  • 1: the Strongly Dominated solutions are excluded from the report. Hs is strongly dominated by Hd, a dominant solution, when Hs ⊃ Hd and Score(Hd) ≥ Score(Hs).
  • 2: the Strongly and Weakly Dominated solutions are excluded from the report. Hw is weakly dominated by Hd when Hw ⊂ Hd and Score(Hd) > Score(Hw).
49053730

Return the Best Solutions

BayesiaLab returns the best solutions generated during the optimization, rather than only the solutions that improved the best score across all populations.

TreeMonitor