PCNN Fold 2

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	12.54%
Test F1 score	0.0920
Hierarchical loss	0.77346340
P-adic loss (total)	1159.81030000
P-adic loss (mean)	0.75755084
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	6,159
Test samples	1,531

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	193	12.61%	0.000000	0.000000
p^4	4	0.26%	0.000000	0.000000
p^3	32	2.09%	0.000002	0.000065
p^2	80	5.23%	0.000160	0.012818
p^1	63	4.11%	0.012658	0.797468
p^0	1,159	75.70%	1.000000	1159.000000

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