PCNN Fold 0

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	24.96%
Test F1 score	0.1984
Hierarchical loss	0.93178360
P-adic loss (total)	366.56146000
P-adic loss (mean)	0.55793220
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	2,766
Test samples	657

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	164	24.96%	0.000000	0.000000
p^3	27	4.11%	0.000003	0.000075
p^2	61	9.28%	0.000198	0.012101
p^1	39	5.94%	0.014085	0.549296
p^0	366	55.71%	1.000000	366.000000

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.