PCNN Fold 1

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	10.71%
Test F1 score	0.0839
Hierarchical loss	0.78728130
P-adic loss (total)	2727.53540000
P-adic loss (mean)	0.58884615
Prime base	83
Hidden layer size	27
Max tags	32
Training samples	18,465
Test samples	4,632

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	496	10.71%	0.000000	0.000000
p^4	1	0.02%	0.000000	0.000000
p^3	182	3.93%	0.000002	0.000318
p^2	615	13.28%	0.000145	0.089273
p^1	618	13.34%	0.012048	7.445783
p^0	2,720	58.72%	1.000000	2720.000000

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.