Cartesian Genetic Programming: Benchmarking

KC Kévin Cortacero
BM Brienne McKenzie
SM Sabina Müller
RK Roxana Khazen
FL Fanny Lafouresse
GC Gaëlle Corsaut
NA Nathalie Van Acker
FF François-Xavier Frenois
LL Laurence Lamant
NM Nicolas Meyer
BV Béatrice Vergier
DW Dennis G. Wilson
HL Hervé Luga
OS Oskar Staufer
MD Michael L. Dustin
SV Salvatore Valitutti
SC Sylvain Cussat-Blanc
request Request a Protocol
ask Ask a question
Favorite

We trained the models with a η=30 nodes, λ=5 offspring over K=20, 000 iterations. If the parent reached a score of 0, the evolution process stopped as no prediction error was made on the training dataset. The mutation probability was μ=0.15 for the functional nodes and ν=0.2 for the outputs. 35 independent runs were made for each experiment for statistical purposes. They were run on a bi Intel Xeon @6140 (2×18 cores, 2.30 GHz − 3.70 GHz) with 192GB of memory.

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

post Post a Question
0 Q&A