PASCAL Agnostic Learning
vs.
Prior Knowledge
IJCNN07

The challenge is now over. But it remains open for post-challenge submissions!


IMPORTANT: Entries made since February 1st 2007 might be using validation data, now available for training.

psmsx_jmlr_run_l

Submitted by H. Jair Escalante

psmsx_jmlr_run_l

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1564 0.1594 0.1686 0.8424 0.8504 0.8304 agnostic
gina 0 0 0.0241 1 1 0.9759 agnostic
hiva 0.0817 0.172 0.2801 0.9137 0.8309 0.7221 agnostic
nova 0 0 0.0527 1 1 0.9486 agnostic
sylva 0.0028 0.0029 0.0062 0.9979 0.9964 0.9938 agnostic
Overall 0.0482 0.0669 0.1063 0.9508 0.9355 0.8941 agnostic

This entry is a complete agnostic learning entry.