Martijho-PathNet-search-plots
From Robin
(Difference between revisions)
(→Training) |
(→Training) |
||
Line 31: | Line 31: | ||
| [[File:Training_accuracy.png|300px|thumb|upright|alt=Training accuracy|Average training accuracy for each of the five search algorithms during the search for each task. The dotted line is the validation accuracy reached after the search was completed.]] | | [[File:Training_accuracy.png|300px|thumb|upright|alt=Training accuracy|Average training accuracy for each of the five search algorithms during the search for each task. The dotted line is the validation accuracy reached after the search was completed.]] | ||
| [[File:Training_value.png|thumb|300px|upright|alt=Training value|Number of training iterations in total for all modules in the PathNet plotted against the cumulative validation accuracy reached for all tasks. The size of the circle corresponds to the amount of modules used.]] | | [[File:Training_value.png|thumb|300px|upright|alt=Training value|Number of training iterations in total for all modules in the PathNet plotted against the cumulative validation accuracy reached for all tasks. The size of the circle corresponds to the amount of modules used.]] | ||
- | | [[File:Used_training_ration.png|thumb|300px|upright|alt=Used Training ratio| | + | | [[File:Used_training_ration.png|thumb|300px|upright|alt=Used Training ratio|Plot of the ratio of unit training in locked and stored modules on the total number of unit training in all modules for each task]] |
|} | |} |
Revision as of 17:48, 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