Martijho-PathNet-search-plots

Fra Robin

(Forskjeller mellom versjoner)
Gå til: navigasjon, søk
(Training)
(Training)
Linje 30: Linje 30:
{|style="margin: 0 auto;"
{|style="margin: 0 auto;"
| [[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|FILLER]]
+
| [[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.]]
| [[File:Used_training_ration.png|thumb|300px|upright|alt=Used Training ratio|FILLER]]
| [[File:Used_training_ration.png|thumb|300px|upright|alt=Used Training ratio|FILLER]]
|}
|}

Versjonen fra 27. feb 2018 kl. 17:41

Innhold

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

Population diversity in recomb search
FILLER
Population diversity in low search
FILLER
Population diversity in high search
FILLER
Population diversity in low2high search
FILLER
Population diversity in high2low search
FILLER


Path size

Path size
FILLER
Layer size
FILLER


Capacity and Reuse

Capacity development during search
FILLER
Capacity vs accuracy
FILLER
Module reuse development during search
FILLER


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.
Used Training ratio
FILLER
Personlige verktøy