PCNN Fold 2

Back to PCNN overview · Back to main index

Fold metrics

MetricValue
Test accuracy11.55%
Test F1 score0.0810
Hierarchical loss0.79697780
P-adic loss (total)1498.42420000
P-adic loss (mean)0.55456114
Prime base79
Hidden layer size27
Max tags32
Training samples10,857
Test samples2,702

P-adic loss breakdown

AgreementCountShareCost per mistakeTotal contribution
Exact match31211.55%0.0000000.000000
p^31184.37%0.0000020.000239
p^235513.14%0.0001600.056882
p^142415.69%0.0126585.367089
p^01,49355.26%1.0000001493.000000

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.