Changes between Version 4 and Version 5 of Documentation/Reference/Genetic Programming Crossovers


Ignore:
Timestamp:
01/31/12 10:58:21 (9 years ago)
Author:
bburlacu
Comment:

Renamed confusing attachment file names and updated image tags.

Legend:

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

    v4 v5  
    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 parameter2.
    1111
    1212=== 2 Probabilistic functional crossover ===
     
    1717- The behavioral distances between node ''i'' and every node ''j'' from `parent1` are computed using a formula that takes into account the minimum and maximum values computed by the two nodes during evaluation:
    1818
    19 [[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/71lyxpreview1.png)]]
     19[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/01-PFX-behavioral-distance.png)]]
    2020
    2121- Once all the behavioral distances between node ''i'' and every node ''j'' have been calculated, they are normalized:
    2222
    23 [[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/72lyxpreview1.png)]]
     23[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/02-PFX-normalized-behavioral-distance.png)]]
    2424 
    2525and turned into selection probabilities (weights):
    2626
    27 [[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/73lyxpreview1.png)]]
     27[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/03-PFX-selection-probabilities.png)]]
    2828 
    2929- A node   from the second parent is probabilistically chosen and swapped with node ''i'' from the first parent
     
    3636- The sampling semantic distance (SSD) between two nodes (subtrees) is defined as the absolute mean between their corresponding sampling semantics:
    3737
    38 [[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/77lyxpreview1.png)]]
     38[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/04-SSX-sampling-semantic-distance.png)]]
    3939
    4040where S1 and S2 are the two subtrees, and ''U'', ''V'' are their respective sampling semantics.
    4141- Two nodes are deemed similar if their SSD falls within a predefined interval [alfa,beta]:
    4242
    43 [[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/83lyxpreview1.png)]]
     43[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/05-SSX-similarity-condition.png)]]
    4444
    4545The crossover procedure chooses a crossover point from `parent0`, then picks the first node in `parent1` that satisfies the similarity condition (5).
     
    5858
    5959=== 6 Depth-constrained crossover ===
    60 The depth-constrained crossover only acts within a specific depth range, in accordance with the DepthRange parameter that can take three values (for a tree of depth ''d'')
    61 - HighLevel (acting on the upper tree levels between 0 and 0.25*d  )
     60The depth-constrained crossover only acts within a specific depth range, in accordance with the !DepthRange parameter that can take three values (for a tree of depth ''d'')
     61- !HighLevel (acting on the upper tree levels between 0 and 0.25*d  )
    6262- Standard (acting on the mid-area of the tree between depth levels 0.25*d and 0.57*d  )
    63 - LowLevel (acting on the lower levels between 0.75*d and d)
     63- !LowLevel (acting on the lower levels between 0.75*d and d)
    6464
    6565=== References ===