PCNN Fold 4

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	10.96%
Test F1 score	0.0881
Hierarchical loss	0.78695273
P-adic loss (total)	2793.53690000
P-adic loss (mean)	0.60244490
Prime base	83
Hidden layer size	27
Max tags	32
Training samples	18,460
Test samples	4,637

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	508	10.96%	0.000000	0.000000
p^3	181	3.90%	0.000002	0.000317
p^2	543	11.71%	0.000145	0.078821
p^1	619	13.35%	0.012048	7.457831
p^0	2,786	60.08%	1.000000	2786.000000

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.