PCNN Fold 3

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	11.68%
Test F1 score	0.0897
Hierarchical loss	0.78802000
P-adic loss (total)	2728.54050000
P-adic loss (mean)	0.58716170
Prime base	83
Hidden layer size	27
Max tags	32
Training samples	18,450
Test samples	4,647

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	543	11.68%	0.000000	0.000000
p^3	196	4.22%	0.000002	0.000343
p^2	568	12.22%	0.000145	0.082450
p^1	619	13.32%	0.012048	7.457831
p^0	2,721	58.55%	1.000000	2721.000000

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 83). Lower values indicate closer predictions in the taxonomy hierarchy. This metric is shared with the umllr model for comparison.