PCNN Fold 3

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	22.46%
Test F1 score	0.1701
Hierarchical loss	0.92951250
P-adic loss (total)	405.43530000
P-adic loss (mean)	0.58758740
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	2,733
Test samples	690

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	155	22.46%	0.000000	0.000000
p^4	8	1.16%	0.000000	0.000000
p^3	28	4.06%	0.000003	0.000078
p^2	64	9.28%	0.000198	0.012696
p^1	30	4.35%	0.014085	0.422535
p^0	405	58.70%	1.000000	405.000000

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