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.

B2

Submitted by The Machine

B2 long run

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.177 0.2242 0.1957 0.9158 0.8698 0.9015 agnostic
gina 0.0108 0.0602 0.0677 0.9997 0.9894 0.9812 agnostic
hiva 0.1922 0.3486 0.3164 0.8958 0.7541 0.752 agnostic
nova 0.1227 0.134 0.1398 0.9642 0.9403 0.9417 agnostic
sylva 0.0042 0.0111 0.0072 0.9997 0.9992 0.9988 agnostic
Overall 0.1014 0.1556 0.1454 0.955 0.9105 0.915 agnostic

This entry is a complete agnostic learning entry.