Martijho-PathNet-search-plots
From Robin
(Difference between revisions)
| Line 24: | Line 24: | ||
| [[File:Capacity_pr_validation_accuracy.png|thumb|300px|upright|alt=Capacity vs accuracy|FILLER]] | | [[File:Capacity_pr_validation_accuracy.png|thumb|300px|upright|alt=Capacity vs accuracy|FILLER]] | ||
| [[File:Module_reuse_pr_generation.png|thumb|300px|upright|alt=Module reuse development during search|FILLER]] | | [[File:Module_reuse_pr_generation.png|thumb|300px|upright|alt=Module reuse development during search|FILLER]] | ||
| + | |} | ||
| + | |||
| + | |||
| + | == Training == | ||
| + | {|style="margin: 0 auto;" | ||
| + | | [[File:Training_accuracy.png|300px|thumb|upright|alt=Training accuracy|FILLER]] | ||
| + | | [[File:Training_value.png|thumb|300px|upright|alt=Training value|FILLER]] | ||
| + | | [[File:Used_training_ration.png|thumb|300px|upright|alt=Used Training ratio|FILLER]] | ||
|} | |} | ||
Revision as of 15:42, 27 February 2018
Contents |
Population Diversity
Population diversity is calculated by the home-made metric of average distance to centroid genotype within each generation, which yields the same results as a pairwise Hamming distance
 |  |  |
 |  |
Path size
 |  |
Capacity and Reuse
 |  |  |
Training
 |  |  |
