PCNN Fold 4

Back to PCNN overview · Back to main index

Fold metrics

MetricValue
Test accuracy11.46%
Test F1 score0.0872
Hierarchical loss0.79275930
P-adic loss (total)1506.07650000
P-adic loss (mean)0.55309457
Prime base79
Hidden layer size27
Max tags32
Training samples10,836
Test samples2,723

P-adic loss breakdown

AgreementCountShareCost per mistakeTotal contribution
Exact match31211.46%0.0000000.000000
p^31174.30%0.0000020.000237
p^231811.68%0.0001600.050953
p^147617.48%0.0126586.025316
p^01,50055.09%1.0000001500.000000

Tag Rank vs First-Layer Weight Magnitude

Tag rank vs max first-layer weight magnitude
Scatter plot showing the relationship between tag battle ranking and maximum absolute first-layer weight value across all hidden units. Shows which input features contribute most to the parameter constrained neural network's hidden representations.

About p-adic loss

P-adic loss measures the distance between predicted and true taxonomy using p-adic metric (base 79). Lower values indicate closer predictions in the taxonomy hierarchy. This metric is shared with the umllr model for comparison.