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.

vrs3

Submitted by Vladimir Nikulin

version3

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1843 0.187 0.1922 0.7882 0.7932 0.7691 agnostic
gina 0 0 0.0266 1 1 0.9761 prior
hiva 0 0 0.3168 0.9983 1 0.5526 agnostic
nova 0 0 0.0816 1 1 0.9248 agnostic
sylva 0.0121 0.0098 0.0144 0.9818 0.9864 0.9803 prior
Overall 0.0393 0.0394 0.1263 0.9537 0.9559 0.8406 prior

This entry is a complete prior knowledge entry.