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.

boost tree

Submitted by JJS

boost tree

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1587 0.1902 0.1825 0.8403 0.7879 0.8075 prior
gina 0.0038 0.0631 0.0901 0.9998 0.9774 0.9653 prior
hiva 0.1885 0.2485 0.3257 0.8743 0.8125 0.7127 agnostic
nova 0.0202 0.042 0.0507 0.9986 0.9854 0.9869 agnostic
sylva 0.0028 0.0041 0.0081 0.9992 0.9981 0.9996 prior
Overall 0.0748 0.1096 0.1314 0.9424 0.9123 0.8944 prior

This entry is a complete prior knowledge entry.