Changes between Version 5 and Version 6 of Documentation/Reference/Genetic Programming Crossovers


Ignore:
Timestamp:
01/31/12 11:00:40 (9 years ago)
Author:
bburlacu
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • Documentation/Reference/Genetic Programming Crossovers

    v5 v6  
    88- It selects a compatible subtree in `parent1` (subject to size limits and grammar constraints)
    99- It performs the swap and returns the (now different) `parent0`
    10 The selection (step 2) above is influenced by a configurable bias towards internal or leaf nodes, given by the !InternalCrossoverPointProbability parameter2.
     10The selection (step 2) above is influenced by a configurable bias towards internal or leaf nodes, given by the !InternalCrossoverPointProbability parameter.
    1111
    1212=== 2 Probabilistic functional crossover ===
     
    5252Given a randomly selected crossover point from `parent1`, context-aware crossover will always find the best location to place the subtree into `parent0`. Because of the initial random step, the context-aware crossover does guarantee that the resulting offspring will be better than its parents. It makes the best choice given a specific piece of genetic material.
    5353The complexity depends on the number of nodes in the first parent, since the algorithm will perform a swap followed by a tree evaluation for every available position, so that it can find out the best insertion point. This means ''n'' evaluations for ''n'' available positions, giving an O(n) complexity.
    54 A discussion of this crossover can be found in [2].
     54A discussion of this crossover can be found in [''2''].
    5555
    5656=== 5 Deterministic-best crossover ===