PCNN Fold 2

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	15.68%
Test F1 score	0.1250
Hierarchical loss	0.92334116
P-adic loss (total)	815.21576000
P-adic loss (mean)	0.65531814
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	4,937
Test samples	1,244

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	195	15.68%	0.000000	0.000000
p^4	2	0.16%	0.000000	0.000000
p^3	55	4.42%	0.000003	0.000154
p^2	93	7.48%	0.000198	0.018449
p^1	85	6.83%	0.014085	1.197183
p^0	814	65.43%	1.000000	814.000000

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.