PCNN Fold 1

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	13.31%
Test F1 score	0.0942
Hierarchical loss	0.77066857
P-adic loss (total)	1167.92660000
P-adic loss (mean)	0.73686224
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	6,105
Test samples	1,585

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	211	13.31%	0.000000	0.000000
p^4	3	0.19%	0.000000	0.000000
p^3	37	2.33%	0.000002	0.000075
p^2	95	5.99%	0.000160	0.015222
p^1	72	4.54%	0.012658	0.911392
p^0	1,167	73.63%	1.000000	1167.000000

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.