PCNN Fold 4

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	25.18%
Test F1 score	0.1823
Hierarchical loss	0.93198264
P-adic loss (total)	394.46268000
P-adic loss (mean)	0.57085770
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	2,732
Test samples	691

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	174	25.18%	0.000000	0.000000
p^4	5	0.72%	0.000000	0.000000
p^3	26	3.76%	0.000003	0.000073
p^2	60	8.68%	0.000198	0.011902
p^1	32	4.63%	0.014085	0.450704
p^0	394	57.02%	1.000000	394.000000

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.