PCNN Fold 0

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	17.30%
Test F1 score	0.1296
Hierarchical loss	0.92481370
P-adic loss (total)	817.79280000
P-adic loss (mean)	0.67032200
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	4,961
Test samples	1,220

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	211	17.30%	0.000000	0.000000
p^4	6	0.49%	0.000000	0.000000
p^3	40	3.28%	0.000003	0.000112
p^2	91	7.46%	0.000198	0.018052
p^1	55	4.51%	0.014085	0.774648
p^0	817	66.97%	1.000000	817.000000

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.