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_run_f1ok

Submitted by H. Jair Escalante

psmsx_run_f1ok

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1685 0.1917 0.1839 0.8362 0.8261 0.8163 agnostic
gina 0 0 0.0241 1 1 0.9758 agnostic
hiva 0.1334 0.1539 0.2986 0.8683 0.8249 0.7029 agnostic
nova 0.1059 0.128 0.0994 0.8955 0.8685 0.9018 agnostic
sylva 0.0077 0.0029 0.0239 0.9919 0.9968 0.9761 agnostic
Overall 0.0831 0.0953 0.126 0.9184 0.9033 0.8746 agnostic

This entry is a complete agnostic learning entry.