PCNN Fold 2

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	21.52%
Test F1 score	0.1593
Hierarchical loss	0.92865527
P-adic loss (total)	418.47620000
P-adic loss (mean)	0.60039630
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	2,726
Test samples	697

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	150	21.52%	0.000000	0.000000
p^4	7	1.00%	0.000000	0.000000
p^3	32	4.59%	0.000003	0.000089
p^2	57	8.18%	0.000198	0.011307
p^1	33	4.73%	0.014085	0.464789
p^0	418	59.97%	1.000000	418.000000

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.