PCNN Fold 2

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	12.15%
Test F1 score	0.0854
Hierarchical loss	0.79585487
P-adic loss (total)	1492.98930000
P-adic loss (mean)	0.56001097
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	10,606
Test samples	2,666

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	324	12.15%	0.000000	0.000000
p^3	138	5.18%	0.000002	0.000280
p^2	326	12.23%	0.000160	0.052235
p^1	390	14.63%	0.012658	4.936709
p^0	1,488	55.81%	1.000000	1488.000000

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.