Changes between Version 1 and Version 2 of Documentation/Reference/Genetic Programming Crossovers

Timestamp:

01/17/12 19:03:53 (13 years ago)

Author:

bburlacu

Comment:

--

Documentation/Reference/Genetic Programming Crossovers

@@ -16 +16 @@
 - A crossover point, corresponding to a node ''i'' is randomly chosen from `parent0`
 - 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:
+
+[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/71lyxpreview1.png)]]
+
 - Once all the behavioral distances between node ''i'' and every node ''j'' have been calculated, they are normalized:
 
-EQ IMAGE HERE
+[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/72lyxpreview1.png)]]
  
 and turned into selection probabilities (weights):
 
-EQ IMAGE HERE
+[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/73lyxpreview1.png)]]
  
 - A node   from the second parent is probabilistically chosen and swapped with node ''i'' from the first parent
@@ -31 +34 @@
 This crossover also follows up on the idea of beneficial exchanges of genetic material, based on a measure of “semantic similarity” as described by Nguyen, et al. in [3, 4].
 - The sampling semantics of a subtree   is defined as the collection of its evaluated values over a sequence of points from the dataset.
-
-EQ IMAGE HERE
-
 - The sampling semantic distance (SSD) between two nodes (subtrees) is defined as the absolute mean between their corresponding sampling semantics:
 
-EQ IMAGE HERE
+[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/77lyxpreview1.png)]]
 
 where S1 and S2 are the two subtrees, and ''U'', ''V'' are their respective sampling semantics.
 - Two nodes are deemed similar if their SSD falls within a predefined interval [alfa,beta]:
 
-EQ IMAGE HERE
+[[Image(http://dev.heuristiclab.com/trac/hl/core/raw-attachment/wiki/Crossovers/83lyxpreview1.png)]]
 
 The crossover procedure chooses a crossover point from `parent0`, then picks the first node in `parent1` that satisfies the similarity condition (5).
@@ -64 +64 @@
 
 References
-[''1''] Bongard, Josh C., "A probabilistic functional crossover operator for genetic programming", in Proceedings of the 12th annual conference on Genetic and evolutionary computation (New York, NY, USA: ACM, 2010), pp. 925--932.
-[''2''] Majeed, Hammad and Ryan, Conor, "Using context-aware crossover to improve the performance of GP", in Proceedings of the 8th annual conference on Genetic and evolutionary computation (New York, NY, USA: ACM, 2006), pp. 847--854.
-[''3''] Uy, Nguyen Quang and O'Neill, Michael and Hoai, Nguyen Xuan and Mckay, Bob and Galván-López, Edgar, "Semantic similarity based crossover in GP: the case for real-valued function regression", in Proceedings of the 9th international conference on Artificial evolution (Berlin, Heidelberg: Springer-Verlag, 2010), pp. 170--181.
-[''4''] Uy, Nguyen Quang and Hoai, Nguyen Xuan and O'Neill, Michael and McKay, Bob, "The role of syntactic and semantic locality of crossover in genetic programming", in Proceedings of the 11th international conference on Parallel problem solving from nature: Part II (Berlin, Heidelberg: Springer-Verlag, 2010), pp. 533--542.
+[''1''] Bongard, Josh C., "A probabilistic functional crossover operator for genetic programming", in Proceedings of the 12th annual conference on Genetic and evolutionary computation (New York, NY, USA: ACM, 2010), pp. 925--932. \\
+[''2''] Majeed, Hammad and Ryan, Conor, "Using context-aware crossover to improve the performance of GP", in Proceedings of the 8th annual conference on Genetic and evolutionary computation (New York, NY, USA: ACM, 2006), pp. 847--854. \\
+[''3''] Uy, Nguyen Quang and O'Neill, Michael and Hoai, Nguyen Xuan and Mckay, Bob and Galván-López, Edgar, "Semantic similarity based crossover in GP: the case for real-valued function regression", in Proceedings of the 9th international conference on Artificial evolution (Berlin, Heidelberg: Springer-Verlag, 2010), pp. 170--181. \\
+[''4''] Uy, Nguyen Quang and Hoai, Nguyen Xuan and O'Neill, Michael and McKay, Bob, "The role of syntactic and semantic locality of crossover in genetic programming", in Proceedings of the 11th international conference on Parallel problem solving from nature: Part II (Berlin, Heidelberg: Springer-Verlag, 2010), pp. 533--542. \\