PCNN Fold 0

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	14.05%
Test F1 score	0.0995
Hierarchical loss	0.77478945
P-adic loss (total)	1126.89890000
P-adic loss (mean)	0.73653525
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	6,160
Test samples	1,530

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	216	14.12%	0.000000	0.000000
p^4	2	0.13%	0.000000	0.000000
p^3	36	2.35%	0.000002	0.000073
p^2	80	5.23%	0.000160	0.012818
p^1	70	4.58%	0.012658	0.886076
p^0	1,126	73.59%	1.000000	1126.000000

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.