PCNN Fold 1

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	16.79%
Test F1 score	0.1208
Hierarchical loss	0.77843976
P-adic loss (total)	744.26715000
P-adic loss (mean)	0.77608670
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	3,621
Test samples	959

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	162	16.89%	0.000000	0.000000
p^4	9	0.94%	0.000000	0.000000
p^3	15	1.56%	0.000002	0.000030
p^2	8	0.83%	0.000160	0.001282
p^1	21	2.19%	0.012658	0.265823
p^0	744	77.58%	1.000000	744.000000

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.