PCNN Fold 2

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	11.22%
Test F1 score	0.0911
Hierarchical loss	0.78723097
P-adic loss (total)	2825.96920000
P-adic loss (mean)	0.61115250
Prime base	83
Hidden layer size	27
Max tags	32
Training samples	18,473
Test samples	4,624

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	519	11.22%	0.000000	0.000000
p^3	181	3.91%	0.000002	0.000317
p^2	533	11.53%	0.000145	0.077370
p^1	572	12.37%	0.012048	6.891566
p^0	2,819	60.96%	1.000000	2819.000000

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.