Martijho-PathNet-search-plots

Fra Robin

(Forskjeller mellom versjoner)
Gå til: navigasjon, søk
(Population Diversity)
(Population Diversity)
Linje 1: Linje 1:
-
== Population Diversity ==  
+
== 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
+
=== Diversity metrics ===
 +
As a calculation of diversity within one population, an average euclidean distance to a population centroid was used for each layer and the averaged. 
 +
 
 +
=== Home-made for each layer ===
{|style="margin: 0 auto;"
{|style="margin: 0 auto;"
| [[File:Population_diversity_recomb.png|300px|thumb|upright|alt=Population diversity in recomb search|Average population diversity for each layer in generation. Experiment: Recomb]]
| [[File:Population_diversity_recomb.png|300px|thumb|upright|alt=Population diversity in recomb search|Average population diversity for each layer in generation. Experiment: Recomb]]

Versjonen fra 28. feb 2018 kl. 14:33

Innhold

Population Diversity

Diversity metrics

As a calculation of diversity within one population, an average euclidean distance to a population centroid was used for each layer and the averaged.

Home-made for each layer

Population diversity in recomb search
Average population diversity for each layer in generation. Experiment: Recomb
Population diversity in low search
Average population diversity for each layer in generation. Experiment: Low
Population diversity in high search
Average population diversity for each layer in generation. Experiment: High
Population diversity in low2high search
Average population diversity for each layer in generation. Experiment: Low to High
Population diversity in high2low search
Average population diversity for each layer in generation. Experiment: High to Low

Path size

Path size
The change in average path size for each generation.
Layer size
The average size of each layer in each optimal path found.

Capacity and Reuse

Capacity development during search
Average number of modules used during the different searches plotted consecutively. The gray dotted line is what number of modules would be used if modules were selected randomly for each task.
Capacity vs accuracy
Used capacity in a PathNet plotted against that networks average classification accuracy for all tasks
Module reuse development during search
Average reuse for each generation plotted for each experiment type. The gray dotted line is what reuse would be reached by random module selection

Training

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.
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.
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
Personlige verktøy