PCNN Fold 1

Back to PCNN overview · Back to main index

Fold metrics

Metric	Value
Test accuracy	16.46%
Test F1 score	0.1173
Hierarchical loss	0.92405810
P-adic loss (total)	782.17944000
P-adic loss (mean)	0.63437100
Prime base	71
Hidden layer size	27
Max tags	32
Training samples	4,948
Test samples	1,233

P-adic loss breakdown

Agreement	Count	Share	Cost per mistake	Total contribution
Exact match	203	16.46%	0.000000	0.000000
p^4	3	0.24%	0.000000	0.000000
p^3	41	3.33%	0.000003	0.000115
p^2	123	9.98%	0.000198	0.024400
p^1	82	6.65%	0.014085	1.154930
p^0	781	63.34%	1.000000	781.000000

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.