PCNN Fold 1

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	11.46%
Test F1 score	0.0843
Hierarchical loss	0.79158425
P-adic loss (total)	1515.36680000
P-adic loss (mean)	0.56925875
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	10,897
Test samples	2,662

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	305	11.46%	0.000000	0.000000
p^3	114	4.28%	0.000002	0.000231
p^2	313	11.76%	0.000160	0.050152
p^1	420	15.78%	0.012658	5.316456
p^0	1,510	56.72%	1.000000	1510.000000

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.