PCNN Fold 3

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	11.45%
Test F1 score	0.0833
Hierarchical loss	0.79712470
P-adic loss (total)	1468.66080000
P-adic loss (mean)	0.54617360
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	10,583
Test samples	2,689

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	308	11.45%	0.000000	0.000000
p^3	145	5.39%	0.000002	0.000294
p^2	330	12.27%	0.000160	0.052876
p^1	443	16.47%	0.012658	5.607595
p^0	1,463	54.41%	1.000000	1463.000000

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.