PCNN Fold 0

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	15.72%
Test F1 score	0.1150
Hierarchical loss	0.77439710
P-adic loss (total)	704.25433000
P-adic loss (mean)	0.79666775
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	3,696
Test samples	884

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	140	15.84%	0.000000	0.000000
p^4	3	0.34%	0.000000	0.000000
p^3	10	1.13%	0.000002	0.000020
p^2	7	0.79%	0.000160	0.001122
p^1	20	2.26%	0.012658	0.253165
p^0	704	79.64%	1.000000	704.000000

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.