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.

little red booster

Submitted by The Machine

If you see my little red booster,
Please drive him home

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1674 0.1996 0.1835 0.9201 0.878 0.9046 agnostic
gina 0.0022 0.0571 0.0622 1 0.991 0.9835 agnostic
hiva 0.1119 0.255 0.2996 0.965 0.7884 0.7614 agnostic
nova 0.1088 0.124 0.1296 0.964 0.931 0.9393 agnostic
sylva 0.0037 0.0107 0.0069 0.9998 0.999 0.9988 agnostic
Overall 0.0788 0.1293 0.1364 0.9698 0.9175 0.9175 agnostic

This entry is a complete agnostic learning entry.