PCNN Fold 3

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	14.72%
Test F1 score	0.1039
Hierarchical loss	0.92247500
P-adic loss (total)	842.06360000
P-adic loss (mean)	0.67744460
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	4,938
Test samples	1,243

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	183	14.72%	0.000000	0.000000
p^4	1	0.08%	0.000000	0.000000
p^3	37	2.98%	0.000003	0.000103
p^2	107	8.61%	0.000198	0.021226
p^1	74	5.95%	0.014085	1.042254
p^0	841	67.66%	1.000000	841.000000

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.