PCNN Fold 2

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	14.60%
Test F1 score	0.0984
Hierarchical loss	0.77212054
P-adic loss (total)	720.38090000
P-adic loss (mean)	0.78472865
Prime base	79
Hidden layer size	27
Max tags	32
Training samples	3,662
Test samples	918

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	135	14.71%	0.000000	0.000000
p^4	1	0.11%	0.000000	0.000000
p^3	25	2.72%	0.000002	0.000051
p^2	7	0.76%	0.000160	0.001122
p^1	30	3.27%	0.012658	0.379747
p^0	720	78.43%	1.000000	720.000000

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.