PCNN Fold 0

Back to PCNN overview · Back to main index

Fold metrics

MetricValue
Test accuracy12.89%
Test F1 score0.0960
Hierarchical loss0.79868317
P-adic loss (total)1494.68270000
P-adic loss (mean)0.54730237
Prime base79
Hidden layer size27
Max tags32
Training samples10,828
Test samples2,731

P-adic loss breakdown

AgreementCountShareCost per mistakeTotal contribution
Exact match35212.89%0.0000000.000000
p^31364.98%0.0000020.000276
p^230911.31%0.0001600.049511
p^144516.29%0.0126585.632911
p^01,48954.52%1.0000001489.000000

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.